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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trois
    -0.06
     shortcomings
    -0.06
    �
    -0.06
     Sr
    -0.06
     fundamental
    -0.06
     triangle
    -0.06
     �
    -0.06
    .Acc
    -0.06
     boosting
    -0.06
    胡
    -0.06
    POSITIVE LOGITS
    (hero
    0.08
     المنت
    0.07
    mise
    0.06
    ισε
    0.06
     namedtuple
    0.06
    دهم
    0.06
    manın
    0.06
    膜
    0.06
    _signature
    0.06
    ования
    0.06
    Act Density 0.035%

    No Known Activations