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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regained
    -0.06
    eldom
    -0.06
    164
    -0.06
    (enable
    -0.06
    แค
    -0.06
     khẩu
    -0.06
     десяти
    -0.06
     представляет
    -0.06
    .should
    -0.06
    startswith
    -0.06
    POSITIVE LOGITS
    -items
    0.06
     spiel
    0.06
    !,↵
    0.06
    batch
    0.06
     homosexual
    0.06
    .DateField
    0.06
    preg
    0.06
    !")↵
    0.06
    ляти
    0.06
     Tac
    0.06
    Act Density 0.028%

    No Known Activations