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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    诚实
    -0.07
    ying
    -0.07
     فيها
    -0.07
    ɥ
    -0.07
    하세요
    -0.06
    elsius
    -0.06
    uzz
    -0.06
    _gl
    -0.06
    kept
    -0.06
    נשים
    -0.06
    POSITIVE LOGITS
     Bear
    0.07
    (TIM
    0.06
     baja
    0.06
    Bruce
    0.06
     Như
    0.06
     Wake
    0.06
     HAVE
    0.06
     searchTerm
    0.06
     porrf
    0.06
    urchase
    0.06
    Act Density 0.001%

    No Known Activations