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

    Neuronpedia

    INDEX
    Explanations

    Code/UI elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fract
    -0.07
    研究所
    -0.06
    Nota
    -0.06
     Guaranteed
    -0.06
     cider
    -0.06
    kus
    -0.06
     Chris
    -0.06
     }</
    -0.06
     perse
    -0.06
    prepend
    -0.06
    POSITIVE LOGITS
    yses
    0.07
    loys
    0.07
    ↵↵↵↵↵↵↵
    0.06
     созд
    0.06
     alcan
    0.06
    esign
    0.06
    ữ
    0.06
    luví
    0.06
    geç
    0.06
    :border
    0.05
    Act Density 0.018%

    No Known Activations