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

    Neuronpedia

    INDEX
    Explanations

    sorting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tracking
    -0.08
    Tracking
    -0.08
     cocos
    -0.07
     valable
    -0.07
     والع
    -0.07
     ORM
    -0.07
     الكثير
    -0.07
    .Duration
    -0.07
    Fullscreen
    -0.07
     tanta
    -0.07
    POSITIVE LOGITS
     alphabetical
    0.14
     alphabet
    0.14
    alphabet
    0.13
     Alphabet
    0.13
     ascending
    0.12
    Alphabet
    0.11
    sorting
    0.11
     lex
    0.11
    sorted
    0.11
     lexi
    0.10
    Act Density 0.014%

    No Known Activations