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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    スタ
    -0.07
     육
    -0.07
    іт
    -0.06
     reflex
    -0.06
    ITERAL
    -0.06
     або
    -0.06
     була
    -0.06
    iator
    -0.06
    ाएग
    -0.06
    UTE
    -0.06
    POSITIVE LOGITS
    {
↵
    0.07
    _linked
    0.07
     may
    0.07
     Marlins
    0.07
     คาส
    0.07
     seized
    0.07
     coursework
    0.07
    .bam
    0.06
    /non
    0.06
    (sq
    0.06
    Act Density 0.004%

    No Known Activations