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

    Neuronpedia

    INDEX
    Explanations

    teepee

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ÇÕES
    0.84
     Evaluación
    0.82
     Distributions
    0.77
     Estadística
    0.77
     Behaviour
    0.76
     Investigación
    0.76
     Forecasting
    0.76
     Payload
    0.76
    صار
    0.76
    Behaviour
    0.76
    POSITIVE LOGITS
    al
    0.91
    alh
    0.84
    an
    0.82
    ml
    0.79
    a
    0.79
    ptr
    0.76
    er
    0.76
    it
    0.76
    ал
    0.74
    all
    0.74
    Act Density 0.000%

    No Known Activations