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

    Neuronpedia

    INDEX
    Explanations

    ask/prompt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     analyses
    -0.07
     Analyzer
    -0.07
     pur
    -0.06
    _func
    -0.06
    auce
    -0.06
    .experimental
    -0.06
    一点
    -0.06
     Inter
    -0.06
     лік
    -0.06
     نفس
    -0.06
    POSITIVE LOGITS
     fict
    0.07
    ,array
    0.07
    νονται
    0.06
     Bergen
    0.06
    ordial
    0.06
     ortam
    0.06
    ––
    0.06
    .priv
    0.06
     amd
    0.06
     Lind
    0.06
    Act Density 0.013%

    No Known Activations