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

    Neuronpedia

    INDEX
    Explanations

    groups of numerical values or parameters

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

    Code punctuation

    np_acts-logits-general · gemini-2.0-flash

    closing parentheses and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.84
    Архівовано
    -0.84
     myſelf
    -0.77
    HostException
    -0.77
     оригіналу
    -0.73
    rrggbb
    -0.72
     FontWeight
    -0.70
     Efq
    -0.69
    LLocation
    -0.69
    GraphicsUnit
    -0.69
    POSITIVE LOGITS
    ):
    0.54
    ):
    0.51
    ↵↵
    0.49
     ]
    0.46
    </em>
    0.46
    '):
    0.46
     ex
    0.46
     */
    0.45
    </i>
    0.45
    ]:
    0.45
    Act Density 0.093%

    No Known Activations