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

    Neuronpedia

    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.74
     complètes
    -0.74
     économies
    -0.68
     leçons
    -0.67
    UnsafeEnabled
    -0.67
    ⓧ
    -0.66
     chré
    -0.64
    LookAnd
    -0.64
     blessés
    -0.63
    seamnă
    -0.63
    POSITIVE LOGITS
     individuals
    0.59
     users
    0.58
     businesses
    0.54
     firms
    0.52
     persons
    0.49
     enterprises
    0.48
     companies
    0.48
    CopyWith
    0.48
    DataAnnotations
    0.47
     enterprise
    0.46
    Act Density 0.016%

    No Known Activations