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

    Neuronpedia

    INDEX
    Explanations

    surprise events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plen
    -0.07
    …but
    -0.06
     všech
    -0.06
     quelques
    -0.06
    PP
    -0.06
    _Db
    -0.06
    pawn
    -0.06
    _OID
    -0.06
     AssemblyCopyright
    -0.06
    Suppress
    -0.06
    POSITIVE LOGITS
    能力
    0.07
    leground
    0.06
     Activities
    0.06
    用品
    0.06
    215
    0.06
    -making
    0.06
     كيل
    0.06
     UserProfile
    0.06
     pictures
    0.06
    classify
    0.06
    Act Density 0.005%

    No Known Activations