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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lara
    -0.06
    таки
    -0.06
    (params
    -0.06
    -scalable
    -0.06
    Opt
    -0.06
    電視
    -0.06
     implemented
    -0.06
     cardi
    -0.06
    标题
    -0.06
    xbf
    -0.05
    POSITIVE LOGITS
    roker
    0.07
    方向
    0.07
     attravers
    0.07
    .Background
    0.06
    /Web
    0.06
    setAttribute
    0.06
     assuming
    0.06
    hton
    0.06
     Lexington
    0.06
    《
    0.06
    Act Density 0.051%

    No Known Activations