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

    Neuronpedia

    INDEX
    Explanations

    begin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     υπό
    -0.07
     Closure
    -0.06
     Вал
    -0.06
     hmac
    -0.06
     Fir
    -0.06
     свобод
    -0.06
     ullam
    -0.06
     Universidad
    -0.06
     reef
    -0.06
    .Response
    -0.06
    POSITIVE LOGITS
    (月
    0.06
    ='',↵
    0.06
    Freq
    0.06
     "-"↵
    0.06
    SerializeField
    0.06
     perks
    0.06
     Bě
    0.06
    (preg
    0.06
     November
    0.06
     leth
    0.06
    Act Density 0.019%

    No Known Activations