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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _refl
    -0.08
    .Transaction
    -0.07
    (scan
    -0.07
     Jared
    -0.07
     giảng
    -0.07
     pepper
    -0.07
    Worksheet
    -0.06
    illance
    -0.06
    尖
    -0.06
    _IL
    -0.06
    POSITIVE LOGITS
     Ther
    0.07
     insanity
    0.06
     contro
    0.06
    .chk
    0.06
     versch
    0.06
    Ž
    0.06
     přibliž
    0.06
     connects
    0.06
    ucks
    0.06
    .defaults
    0.06
    Act Density 0.027%

    No Known Activations