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

    Neuronpedia

    INDEX
    Explanations

    configuration, licensing, tools, male

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moris
    0.40
    我们就
    0.39
    faite
    0.39
     MOR
    0.38
     customary
    0.37
    有名
    0.37
    antad
    0.36
     விட்டு
    0.36
     செய்யும்
    0.36
    bete
    0.36
    POSITIVE LOGITS
    ुल
    0.41
    uintes
    0.38
    UpdatedAt
    0.38
    ీ
    0.38
    يل
    0.37
    قتل
    0.36
     tabpos
    0.36
    ícios
    0.36
    騫
    0.36
    ған
    0.35
    Act Density 0.000%

    No Known Activations