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

    Neuronpedia

    INDEX
    Explanations

    oscillator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рест
    -0.08
     чт
    -0.07
    pañ
    -0.07
    不幸
    -0.07
    组团
    -0.07
    Fold
    -0.07
     misunderstood
    -0.07
    relationships
    -0.07
     cope
    -0.07
     tz
    -0.07
    POSITIVE LOGITS
     Quality
    0.07
    ger
    0.06
    ément
    0.06
    锋
    0.06
    下面
    0.06
    ㈮
    0.06
     However
    0.06
    евой
    0.06
    Damage
    0.06
     Crusher
    0.06
    Act Density 0.004%

    No Known Activations