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

    Neuronpedia

    INDEX
    Explanations

    repair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atre
    -0.07
     dear
    -0.06
    _validation
    -0.06
    劫
    -0.06
    /location
    -0.06
     travelled
    -0.06
     farms
    -0.06
     Lamp
    -0.06
     m
    -0.06
    جب
    -0.06
    POSITIVE LOGITS
     koje
    0.08
    ▨
    0.07
    男方
    0.07
    fur
    0.07
    ประต
    0.07
    ǀ
    0.07
     finalists
    0.07
    hooks
    0.07
     maçı
    0.07
     vag
    0.07
    Act Density 0.014%

    No Known Activations