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

    Neuronpedia

    INDEX
    Explanations

    spam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OPEN
    -0.07
    acency
    -0.06
     Prix
    -0.06
     от
    -0.06
     immutable
    -0.06
    घ
    -0.06
     pipes
    -0.06
     Titan
    -0.06
    \"></
    -0.06
    ensible
    -0.06
    POSITIVE LOGITS
    Canadian
    0.07
    =time
    0.07
     spam
    0.07
    (as
    0.07
     звіль
    0.06
    -An
    0.06
    .avi
    0.06
     vysvět
    0.06
     ):↵↵
    0.06
    ategori
    0.06
    Act Density 0.003%

    No Known Activations