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

    Neuronpedia

    INDEX
    Explanations

    academic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Van
    -0.07
    \Collections
    -0.07
    kola
    -0.07
     momentum
    -0.06
     جذ
    -0.06
    Choice
    -0.06
     Kazakhstan
    -0.06
     Pet
    -0.06
    ₁
    -0.06
    jh
    -0.06
    POSITIVE LOGITS
     самых
    0.07
    /Admin
    0.07
     bystand
    0.06
    xac
    0.06
    よび
    0.06
    _GAME
    0.06
     sigmoid
    0.06
     Ś
    0.06
     цик
    0.06
    accept
    0.06
    Act Density 0.027%

    No Known Activations