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

    Neuronpedia

    INDEX
    Explanations

    stop words/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thị
    -0.07
     Ctrl
    -0.07
     scarf
    -0.06
     kommer
    -0.06
     projectile
    -0.06
    justify
    -0.06
    .fhir
    -0.06
    	EIF
    -0.06
    figur
    -0.06
    ?('
    -0.06
    POSITIVE LOGITS
    ودة
    0.07
    .savefig
    0.07
     driving
    0.07
    _dispatcher
    0.06
     있을
    0.06
    ladı
    0.06
     brat
    0.06
     meaningful
    0.06
     adverse
    0.06
     obviously
    0.06
    Act Density 0.278%

    No Known Activations