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

    Neuronpedia

    INDEX
    Explanations

    Clear/reset functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鹅
    -0.07
    Equivalent
    -0.07
    촣
    -0.07
    プレゼント
    -0.07
    )object
    -0.07
    anden
    -0.06
    Sir
    -0.06
     Rough
    -0.06
    _pipe
    -0.06
     useParams
    -0.06
    POSITIVE LOGITS
    宁波
    0.07
    ocrats
    0.07
     STM
    0.07
    ⤵
    0.07
    stdcall
    0.07
    (weights
    0.06
     Belt
    0.06
    '][$
    0.06
     Greeks
    0.06
     Estado
    0.06
    Act Density 0.003%

    No Known Activations