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

    Neuronpedia

    INDEX
    Explanations

    Roger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :%
    -0.08
    xca
    -0.08
    ブラ
    -0.08
     بإ
    -0.08
    THR
    -0.07
    Ba
    -0.07
    payments
    -0.07
     bull
    -0.07
    %D
    -0.07
    utomation
    -0.07
    POSITIVE LOGITS
    ﮅ
    0.07
    ┰
    0.07
     ancest
    0.06
    (reason
    0.06
    ĵ
    0.06
    ucer
    0.06
    字样
    0.06
    Converter
    0.06
    .SYSTEM
    0.06
     Regex
    0.06
    Act Density 0.003%

    No Known Activations