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

    Neuronpedia

    INDEX
    Explanations

    Heck/Hell

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Iter
    -0.07
    ito
    -0.07
     kur
    -0.07
    w
    -0.06
    Hour
    -0.06
     zombie
    -0.06
    ritos
    -0.06
    bz
    -0.06
    raphics
    -0.06
    ivity
    -0.06
    POSITIVE LOGITS
     scrolled
    0.07
     Lah
    0.07
    Що
    0.06
     �
    0.06
    animals
    0.06
    .getInput
    0.06
     конструкции
    0.06
    ingles
    0.06
     بلند
    0.06
    -regexp
    0.06
    Act Density 0.002%

    No Known Activations