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

    Neuronpedia

    INDEX
    Explanations

    causes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Used
    0.45
     usado
    0.45
    Leading
    0.43
     usados
    0.43
     utilisé
    0.42
     Used
    0.42
     utilizado
    0.41
    用于
    0.41
     usato
    0.40
     Leading
    0.40
    POSITIVE LOGITS
     caused
    1.13
     helped
    1.09
     spurred
    1.06
    caused
    1.01
     propelled
    0.99
     enabled
    0.96
     fuelled
    0.94
     prompted
    0.93
     sparked
    0.92
     allowed
    0.91
    Act Density 0.329%

    No Known Activations