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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     majet
    -0.06
    [mid
    -0.06
     bath
    -0.06
    itag
    -0.06
     abych
    -0.06
    _FACTORY
    -0.05
     ав
    -0.05
    !(↵
    -0.05
     pelos
    -0.05
    _sentence
    -0.05
    POSITIVE LOGITS
     available
    0.07
    신
    0.07
    "});↵
    0.07
    يع
    0.07
    こんな
    0.07
    slide
    0.06
     erosion
    0.06
    purpose
    0.06
    <option
    0.06
    ��
    0.06
    Act Density 0.014%

    No Known Activations