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

    Neuronpedia

    INDEX
    Explanations

    coding and technical keywords related to programming structures and types

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

    C language structures and bitfields

    np_acts-logits-general · gemini-2.0-flash

    Python dunder methods and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.64
     PDA
    -0.58
     gfx
    -0.58
     ErrIntOverflow
    -0.55
    tvguidetime
    -0.55
     Administrativna
    -0.54
    PCP
    -0.53
     Moffat
    -0.53
     Koy
    -0.53
    ConstraintMaker
    -0.53
    POSITIVE LOGITS
     __
    2.77
    __
    2.73
    .__
    1.97
    (__
    1.94
    )__
    1.81
     (__
    1.70
    ___
    1.67
    __.
    1.63
    ____
    1.62
     "__
    1.59
    Act Density 0.314%

    No Known Activations