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

    Neuronpedia

    INDEX
    Explanations

    Saving and investing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ThanOrEqualTo
    -0.08
    (models
    -0.07
     shuffled
    -0.06
     knih
    -0.06
     Worksheet
    -0.06
     sovereignty
    -0.06
     ignorant
    -0.06
    foreground
    -0.06
    отя
    -0.06
    :description
    -0.06
    POSITIVE LOGITS
    /gl
    0.07
    ประเทศไทย
    0.06
    imbledon
    0.06
     euth
    0.06
    riters
    0.06
    acet
    0.06
     IA
    0.06
     ears
    0.06
    asc
    0.06
    爱
    0.06
    Act Density 0.024%

    No Known Activations