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

    Neuronpedia

    INDEX
    Explanations

    tilde for version specs or paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?</
    0.52
     горо
    0.50
    。</
    0.49
    uais
    0.48
    lerde
    0.48
    ্ে
    0.47
     сезо
    0.47
     fournisseur
    0.46
     ля
    0.46
     мнение
    0.46
    POSITIVE LOGITS
     quasi
    0.70
     near
    0.61
     as
    0.59
     pseudo
    0.59
    ست
    0.57
    ك
    0.57
    크
    0.57
     pseud
    0.56
    ת
    0.55
    어
    0.55
    Act Density 0.022%

    No Known Activations