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

    Neuronpedia

    INDEX
    Explanations

    ar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("%.
    -0.07
    _Build
    -0.07
     publishes
    -0.06
    �
    -0.06
     воно
    -0.06
    ("[%
    -0.06
     kodu
    -0.06
    本当に
    -0.06
    �은
    -0.06
    ThreadId
    -0.06
    POSITIVE LOGITS
    ar
    0.09
    or
    0.08
    ur
    0.07
    AR
    0.07
    MAN
    0.07
    ars
    0.07
    ø
    0.07
    OR
    0.07
    ra
    0.07
    ARS
    0.06
    Act Density 0.001%

    No Known Activations