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

    Neuronpedia

    INDEX
    Explanations

    opensource

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ")]↵
    -0.07
     Drop
    -0.07
    wor
    -0.07
    ()])↵
    -0.06
    "])
↵
    -0.06
     glyphs
    -0.06
    etyl
    -0.06
     contraction
    -0.06
    format
    -0.06
    succ
    -0.06
    POSITIVE LOGITS
    opensource
    0.09
    .clean
    0.07
     правиль
    0.07
     Leadership
    0.07
     Foley
    0.06
     Enough
    0.06
    わけ
    0.06
    =false
    0.06
     Unless
    0.06
    /story
    0.06
    Act Density 0.000%

    No Known Activations