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

    Neuronpedia

    INDEX
    Explanations

    conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conditions
    -2.95
    conditions
    -2.30
     Conditions
    -2.22
     CONDITIONS
    -2.08
    Conditions
    -1.96
     condiciones
    -1.63
    CONDITIONS
    -1.59
     condition
    -1.52
     condições
    -1.50
     Bedingungen
    -1.50
    POSITIVE LOGITS
     виправивши
    0.92
     متعلقه
    0.84
    ⓧ
    0.83
    MLLoader
    0.81
    ształ
    0.79
    løs
    0.79
     réguli
    0.78
     mourir
    0.73
     ModelExpression
    0.72
    __":
    0.71
    Act Density 0.043%

    No Known Activations