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

    Neuronpedia

    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FileInfo
    -0.07
    광
    -0.06
    .organization
    -0.06
    .restaurant
    -0.06
    -active
    -0.06
    .utc
    -0.06
    23
    -0.06
     kendisine
    -0.06
    ández
    -0.06
     Leaders
    -0.06
    POSITIVE LOGITS
    ambil
    0.07
    してる
    0.07
     ffm
    0.07
     bên
    0.06
     applyMiddleware
    0.06
    GetMethod
    0.06
    Bước
    0.06
    ベル
    0.06
    )::
    0.06
    椅
    0.06
    Act Density 0.004%

    No Known Activations