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

    Neuronpedia

    INDEX
    Explanations

    look

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FF
    -0.08
     Ara
    -0.08
    ulence
    -0.07
     Dense
    -0.07
    穜
    -0.07
     coaching
    -0.07
     Pent
    -0.07
     Permanent
    -0.07
    .Unmarshal
    -0.07
    Confirmation
    -0.07
    POSITIVE LOGITS
    小鸟
    0.07
     nied
    0.06
     così
    0.06
    嘀
    0.06
    鹊
    0.06
    ܩ
    0.06
    曳
    0.06
    ஓ
    0.06
     Тем
    0.06
    animal
    0.06
    Act Density 0.036%

    No Known Activations