Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or logical symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical indices and exponents in formulas.

    oai_token-act-pair · claude-4-5-haikuTriggered by @kparkhamchuk
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.78
    </code>
    -0.65
    })}\
    -0.63
    </strong>
    -0.63
    ”!
    -0.61
     فريبيس
    -0.60
    ”?
    -0.58
    "!
    -0.58
    ])))
    -0.57
    ].)
    -0.55
    POSITIVE LOGITS
    Архівовано
    0.66
    magini
    0.61
     Мексичка
    0.60
    хьтан
    0.58
    iestety
    0.56
    visuel
    0.55
    Getenv
    0.55
    kháu
    0.54
    SourceChecksum
    0.54
    astify
    0.52
    Act Density 0.710%

    No Known Activations