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

    Neuronpedia

    INDEX
    Explanations

    database code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     частини
    -0.06
     secondo
    -0.06
     sonrası
    -0.06
     otras
    -0.06
    ETERS
    -0.06
     itibaren
    -0.06
     свою
    -0.06
    战争
    -0.06
     phiếu
    -0.06
     crashes
    -0.06
    POSITIVE LOGITS
    read
    0.07
    chie
    0.07
    琳
    0.07
     dread
    0.06
     arr
    0.06
     Godzilla
    0.06
    osoph
    0.06
    서울
    0.06
    ldr
    0.06
    ivor
    0.06
    Act Density 0.007%

    No Known Activations