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

    Neuronpedia

    INDEX
    Explanations

    equals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (>
    -0.09
     agro
    -0.07
    itario
    -0.07
     germ
    -0.07
    hiro
    -0.07
     Prosper
    -0.07
     Daddy
    -0.07
     tərəfindən
    -0.07
     daddy
    -0.06
     remain
    -0.06
    POSITIVE LOGITS
    difference
    0.15
     difference
    0.15
     فرق
    0.15
     اختلاف
    0.14
     diferença
    0.14
     differences
    0.14
     diferenças
    0.14
     Differences
    0.13
    _difference
    0.13
     différences
    0.13
    Act Density 0.038%

    No Known Activations