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

    Neuronpedia

    INDEX
    Explanations

    mathematical terminology and relationships within equations

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

    Mathematical notation/symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -1.00
    tagHelperRunner
    -0.58
    sidemargin
    -0.57
    hoeddwyd
    -0.57
    )))),
    -0.56
    }}}
    -0.55
    Chham
    -0.53
    })),
    -0.53
     ""],
    -0.53
    })]
    -0.52
    POSITIVE LOGITS
     المعيارى
    0.86
     שוליים
    0.75
    PyExc
    0.66
     Others
    0.65
     others
    0.65
    󠁢
    0.64
    깥
    0.63
    phazard
    0.62
     Waray
    0.60
    others
    0.60
    Act Density 2.379%

    No Known Activations