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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relacion
    -0.08
     trumpet
    -0.08
     executes
    -0.07
    _ttl
    -0.07
     Pension
    -0.07
    מטופ
    -0.07
    .rawValue
    -0.07
    פגע
    -0.07
     setColor
    -0.07
    Immutable
    -0.06
    POSITIVE LOGITS
     grades
    0.08
     How
    0.07
     Title
    0.07
     exploded
    0.07
    olding
    0.07
     Time
    0.07
    좌
    0.06
    KS
    0.06
     חדר
    0.06
     Gap
    0.06
    Act Density 0.003%

    No Known Activations