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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Color
    -0.08
    _reserved
    -0.07
     Matter
    -0.07
    سط
    -0.07
     Confidence
    -0.07
    Jack
    -0.06
    ucson
    -0.06
    stoupil
    -0.06
     den
    -0.06
    lepší
    -0.06
    POSITIVE LOGITS
     соответ
    0.07
     tenure
    0.07
     regularly
    0.06
     مشاه
    0.06
     Elig
    0.06
     casualty
    0.06
    .layoutControlItem
    0.06
     EntryPoint
    0.06
     cellular
    0.06
     จำก
    0.06
    Act Density 0.084%

    No Known Activations