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

    Neuronpedia

    INDEX
    Explanations

    xml

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ده
    -0.07
     harmed
    -0.07
    geries
    -0.06
    beta
    -0.06
    璃
    -0.06
    cript
    -0.06
    거나
    -0.06
     Damn
    -0.06
     Caesar
    -0.06
    txt
    -0.06
    POSITIVE LOGITS
    .tagName
    0.07
     grabbing
    0.07
    toInt
    0.06
    γκ
    0.06
    深圳
    0.06
    .bb
    0.06
    Democrats
    0.06
    (it
    0.06
    (Int
    0.06
    _Response
    0.06
    Act Density 0.000%

    No Known Activations