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

    Neuronpedia

    INDEX
    Explanations

    Code/document snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alike
    -0.07
    .MapPath
    -0.07
     rats
    -0.07
    .imread
    -0.06
     uf
    -0.06
    ㇻ
    -0.06
    'l
    -0.06
    '↵↵↵↵
    -0.06
     pricey
    -0.06
     val
    -0.06
    POSITIVE LOGITS
    Strike
    0.08
    PF
    0.08
     pronto
    0.08
    普法
    0.07
     entrada
    0.07
    쎄
    0.07
     Gateway
    0.07
    过渡
    0.07
     seguro
    0.07
    ieces
    0.07
    Act Density 0.230%

    No Known Activations