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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lucky
    -0.07
    oultry
    -0.07
    .Pos
    -0.07
     Patt
    -0.07
    edBy
    -0.06
     الفلسطيني
    -0.06
    rganization
    -0.06
     PIT
    -0.06
     rar
    -0.06
     référence
    -0.06
    POSITIVE LOGITS
     drop
    0.08
    叙述
    0.07
    ']),
    0.07
    ），
    0.07
    "),
    0.07
    "]↵
    0.07
    %).↵↵
    0.07
     broaden
    0.07
    خي
    0.07
    ﹼ
    0.07
    Act Density 0.007%

    No Known Activations