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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     admir
    -0.07
     κο
    -0.06
     frozen
    -0.06
    SACTION
    -0.06
    trx
    -0.06
    }{
    -0.06
     تصو
    -0.06
    :f
    -0.06
    _attrs
    -0.06
     broke
    -0.06
    POSITIVE LOGITS
     STATIC
    0.07
     المعلومات
    0.07
    _dispatcher
    0.07
    Defense
    0.07
     поможет
    0.06
     Definitions
    0.06
     딸
    0.06
     澳
    0.06
     XM
    0.06
     Malk
    0.06
    Act Density 0.076%

    No Known Activations