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

    Neuronpedia

    INDEX
    Explanations

    determined

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Err
    -0.07
    stract
    -0.07
    ulture
    -0.06
    ->
    -0.06
    صيد
    -0.06
     Arb
    -0.06
     jud
    -0.06
    大会
    -0.06
    ((&___
    -0.06
    POSITIVE LOGITS
    仑
    0.08
    よい
    0.07
    гу
    0.07
    )const
    0.07
     ajout
    0.07
    getData
    0.07
    باقي
    0.07
    первых
    0.07
    couldn
    0.07
    бит
    0.07
    Act Density 0.015%

    No Known Activations