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

    Neuronpedia

    INDEX
    Explanations

    legal contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interactive
    -0.08
    Thinking
    -0.06
    ombo
    -0.06
    >Select
    -0.06
     Leisure
    -0.06
    Priv
    -0.06
    .Put
    -0.06
    ی
    -0.06
    ốt
    -0.06
     headlights
    -0.06
    POSITIVE LOGITS
     Boiler
    0.07
    (fabs
    0.07
     kullan
    0.07
     chrono
    0.06
    後に
    0.06
    με
    0.06
     Created
    0.06
    ynchron
    0.06
     провести
    0.06
     đen
    0.06
    Act Density 0.062%

    No Known Activations