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

    Neuronpedia

    INDEX
    Explanations

    stopwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     semaine
    -0.08
     lã
    -0.07
     Rey
    -0.07
     mé
    -0.06
    entialAction
    -0.06
    _Up
    -0.06
    เหต
    -0.06
    Monitor
    -0.06
     grab
    -0.06
     italiane
    -0.06
    POSITIVE LOGITS
    earned
    0.07
     conf
    0.06
    conf
    0.06
    cargo
    0.06
    oseconds
    0.06
    aston
    0.06
    anden
    0.06
     توضی
    0.06
    [label
    0.06
    bles
    0.06
    Act Density 0.047%

    No Known Activations