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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raises
    -0.09
    قام
    -0.09
    اضيع
    -0.08
    /detail
    -0.08
    比分
    -0.08
     Pres
    -0.08
     Moran
    -0.08
     Excellent
    -0.08
     Cant
    -0.08
     Towers
    -0.08
    POSITIVE LOGITS
     prefixes
    0.13
    Prefixes
    0.12
     prefix
    0.11
    prefix
    0.10
    _prefix
    0.10
    Prefix
    0.09
     Prefix
    0.09
    (prefix
    0.09
    PREFIX
    0.09
    .prefix
    0.09
    Act Density 0.002%

    No Known Activations