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

    Neuronpedia

    INDEX
    Explanations

    Time duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    渥
    -0.07
     payable
    -0.07
    ymce
    -0.07
     ethereum
    -0.07
    (todo
    -0.07
     HEL
    -0.07
     darauf
    -0.07
     orientations
    -0.07
    バランス
    -0.07
    ạo
    -0.06
    POSITIVE LOGITS
     hose
    0.07
    学问
    0.07
    ݓ
    0.06
    (`/
    0.06
     아마
    0.06
     simply
    0.06
    异地
    0.06
    üş
    0.06
     был
    0.06
    礓
    0.06
    Act Density 0.035%

    No Known Activations