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

    Neuronpedia

    INDEX
    Explanations

    countable nouns associated with numerical values or rankings

    oai_token-act-pair · gemini-2.0-flash

    technical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reſ
    -0.71
    hésite
    -0.70
     Diſ
    -0.68
     Conſ
    -0.65
     Perſ
    -0.63
     purpoſe
    -0.61
    RegressionTest
    -0.61
     Inſ
    -0.59
    kespea
    -0.59
     Tenggara
    -0.58
    POSITIVE LOGITS
    UpInside
    0.75
     GenerationType
    0.66
    
    0.65
    OGND
    0.63
    AnimationsModule
    0.63
    EndInit
    0.59
    PerformLayout
    0.56
     incumbent
    0.56
    AutoScaleMode
    0.54
     incumb
    0.54
    Act Density 3.224%

    No Known Activations