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

    Neuronpedia

    INDEX
    Explanations

    terrorist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     อ
    -0.07
    batim
    -0.07
    Cole
    -0.06
     colder
    -0.06
     salvation
    -0.06
     پزشکی
    -0.06
    -character
    -0.06
    _micro
    -0.06
    Saturday
    -0.06
     çünkü
    -0.06
    POSITIVE LOGITS
    _missing
    0.07
    $,
    0.07
    ịp
    0.06
    (Position
    0.06
    pees
    0.06
    /'↵
    0.06
    (pid
    0.06
    (inner
    0.06
    丰
    0.06
     rp
    0.06
    Act Density 0.002%

    No Known Activations