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

    Neuronpedia

    INDEX
    Explanations

    rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rate
    -1.63
    rate
    -1.41
     rates
    -1.33
     Rate
    -1.30
     RATE
    -1.21
    Rate
    -1.19
    rates
    -1.16
     Rates
    -1.13
    RATE
    -1.09
    Rates
    -1.04
    POSITIVE LOGITS
    oflavin
    0.66
    ubov
    0.65
     hepat
    0.60
    DockStyle
    0.58
    ercizio
    0.57
    DataMember
    0.54
    cody
    0.53
     cysts
    0.53
    出版年
    0.53
    ecuzione
    0.52
    Act Density 0.343%

    No Known Activations