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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     houſe
    -0.71
     themſelves
    -0.70
     Diſ
    -0.69
     Majefty
    -0.68
     Conſ
    -0.68
     poffe
    -0.68
     Chriftian
    -0.65
     greateſt
    -0.63
     itſelf
    -0.61
     Houſe
    -0.60
    POSITIVE LOGITS
    astify
    0.60
    脚注の使い方
    0.60
     pageable
    0.54
    SharedCtor
    0.54
    ंदीखरीदारी
    0.54
    AnimationsModule
    0.52
    Hochspringen
    0.52
    دانشنامهٔ
    0.51
     Chwiliwch
    0.51
     /\.(
    0.50
    Act Density 0.011%

    No Known Activations