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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    long sequences of text that include specific coding structures and syntax.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    DOMNode
    -0.08
    زمان
    -0.07
    .Part
    -0.07
     Engl
    -0.06
    ال
    -0.06
     _(
    -0.06
    /mol
    -0.06
     insanların
    -0.06
    _des
    -0.06
     humanoid
    -0.06
    POSITIVE LOGITS
    atra
    0.06
    ẻ
    0.06
     backing
    0.06
     whim
    0.06
    除了
    0.06
     clr
    0.06
     wore
    0.06
    lac
    0.06
    重要
    0.05
    fic
    0.05
    Act Density 0.009%

    No Known Activations