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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ænd
    -0.07
     lịch
    -0.06
    urile
    -0.06
    alled
    -0.06
    :class
    -0.06
     бо
    -0.06
    spar
    -0.06
     поп
    -0.06
    -driven
    -0.06
    _choice
    -0.06
    POSITIVE LOGITS
     knife
    0.06
     Microsoft
    0.06
    ук
    0.06
     kob
    0.06
     cottage
    0.06
    .parentNode
    0.06
     amount
    0.06
     giờ
    0.06
    497
    0.06
     рекоменда
    0.06
    Act Density 0.003%

    No Known Activations