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

    Neuronpedia

    INDEX
    Explanations

    foreign characters and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    matics
    0.47
     dissemination
    0.44
     ![
    0.40
     scall
    0.39
     многим
    0.39
     disseminated
    0.39
    setlength
    0.38
    idunt
    0.38
     averse
    0.38
     gods
    0.38
    POSITIVE LOGITS
    Promise
    0.41
    arios
    0.41
    ARA
    0.40
    ارا
    0.39
    Bachelor
    0.39
    ሮ
    0.38
    asr
    0.38
    зов
    0.37
    燚
    0.37
    osh
    0.37
    Act Density 0.000%

    No Known Activations