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

    Neuronpedia

    INDEX
    Explanations

    .createStatement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Orb
    -0.07
     contro
    -0.06
    wipe
    -0.06
     Pyongyang
    -0.06
    tection
    -0.06
    in
    -0.06
    ويل
    -0.06
     HAL
    -0.06
    >x
    -0.06
    Rub
    -0.06
    POSITIVE LOGITS
    .createStatement
    0.08
    したら
    0.07
    ='\
    0.07
     Прав
    0.06
    settings
    0.06
    .generate
    0.06
     فوق
    0.06
     SMALL
    0.06
    اعة
    0.06
     formulated
    0.06
    Act Density 0.001%

    No Known Activations