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

    Neuronpedia

    INDEX
    Explanations

    PHP

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ặc
    -0.07
    orted
    -0.07
     authority
    -0.07
    gest
    -0.07
    IMG
    -0.06
     Director
    -0.06
    (textBox
    -0.06
    万名
    -0.06
    딘
    -0.06
    Luke
    -0.06
    POSITIVE LOGITS
     vais
    0.07
     sid
    0.07
     sights
    0.07
     начала
    0.07
    =\"
    0.06
    ;k
    0.06
     Packers
    0.06
     $(
    0.06
     תע
    0.06
    ировка
    0.06
    Act Density 0.021%

    No Known Activations