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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     essen
    -0.08
    臭
    -0.07
    OAD
    -0.07
    れ
    -0.07
    抔
    -0.07
    บำ
    -0.07
    椽
    -0.07
    ilege
    -0.07
    .toast
    -0.07
     communicate
    -0.07
    POSITIVE LOGITS
     helf
    0.07
    teborg
    0.07
    ']){↵
    0.07
     @_;↵
    0.07
    Arduino
    0.07
     contest
    0.07
    Argentina
    0.06
     Artem
    0.06
    的趋势
    0.06
    이다
    0.06
    Act Density 0.076%

    No Known Activations