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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Significant
    -0.07
    [text
    -0.07
     ['/
    -0.06
     Administrative
    -0.06
    _o
    -0.06
     Tarih
    -0.06
    -0.06
     admits
    -0.06
    _NOTICE
    -0.06
    carousel
    -0.06
    POSITIVE LOGITS
    cles
    0.07
    (tree
    0.07
     apologise
    0.07
    мотря
    0.06
    :UIControl
    0.06
    -caret
    0.06
    vik
    0.06
    ือข
    0.06
    빙
    0.06
    bank
    0.06
    Act Density 0.008%

    No Known Activations