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

    Neuronpedia

    INDEX
    Explanations

    library OS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.98
    ありません
    0.88
     energético
    0.85
    2
    0.85
    larına
    0.84
     тема
    0.84
    大
    0.82
    お金
    0.80
     ребен
    0.80
    se
    0.79
    POSITIVE LOGITS
    า
    1.27
    k
    1.21
    ة
    1.14
    ী
    1.11
    ים
    1.09
    ן
    1.09
    us
    1.06
    ad
    1.05
     to
    1.05
    ন
    1.02
    Act Density 0.026%

    No Known Activations