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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     who
    -0.07
    ù
    -0.07
     stats
    -0.07
    >User
    -0.07
    대의
    -0.07
    уки
    -0.07
     phot
    -0.06
     sanitation
    -0.06
    落
    -0.06
    306
    -0.06
    POSITIVE LOGITS
     spíše
    0.06
    acking
    0.06
    işi
    0.06
    讀
    0.06
    .FlatAppearance
    0.06
    _behavior
    0.06
     نام
    0.06
     believable
    0.06
    ительное
    0.06
    .and
    0.06
    Act Density 0.002%

    No Known Activations