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

    Neuronpedia

    INDEX
    Explanations

    demonstrate confidence and effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.74
    м
    0.64
    ER
    0.54
    SYSTEM
    0.54
    พลาด
    0.53
    સ
    0.52
    મ
    0.49
    솝
    0.49
    ので
    0.47
    オブジェクト
    0.47
    POSITIVE LOGITS
    tien
    0.49
     Yee
    0.44
     PCE
    0.44
     Timberwolves
    0.43
     Performances
    0.43
    pues
    0.41
    til
    0.41
    Portug
    0.41
     graduation
    0.41
    狠狠
    0.41
    Act Density 0.000%

    No Known Activations