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

    Neuronpedia

    INDEX
    Explanations

    Men's blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ไม
    -0.08
     следующ
    -0.08
    頃
    -0.07
    _META
    -0.07
     cerca
    -0.07
    (op
    -0.07
     около
    -0.07
    妇
    -0.07
    -п
    -0.07
     eben
    -0.07
    POSITIVE LOGITS
    '";
↵
    0.06
     operand
    0.06
     муницип
    0.06
     хол
    0.06
    Instead
    0.05
    awning
    0.05
    agnar
    0.05
    OfYear
    0.05
    /filepath
    0.05
    ＝＝
    0.05
    Act Density 0.264%

    No Known Activations