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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cancellationToken
    -0.07
     forall
    -0.07
    .anim
    -0.07
    .age
    -0.07
     Hun
    -0.07
    .isSuccessful
    -0.06
    اخبار
    -0.06
     childbirth
    -0.06
    宠
    -0.06
    .Warn
    -0.06
    POSITIVE LOGITS
    ля
    0.07
    كلف
    0.07
    tığı
    0.07
    糟糕
    0.06
    Los
    0.06
    óg
    0.06
    _attention
    0.06
    �
    0.06
    했다
    0.06
    tiği
    0.06
    Act Density 0.007%

    No Known Activations