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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    28
    -0.06
     unhealthy
    -0.06
    Independent
    -0.06
     рав
    -0.06
    lıkları
    -0.06
    од
    -0.06
    ID
    -0.06
     změny
    -0.06
    -safe
    -0.06
    гів
    -0.06
    POSITIVE LOGITS
    .Expressions
    0.06
    /wait
    0.06
    grave
    0.06
    /m
    0.06
     Σ
    0.06
    ‌د
    0.06
    _plots
    0.06
    降
    0.06
     مبت
    0.06
    angled
    0.06
    Act Density 0.046%

    No Known Activations