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

    Neuronpedia

    INDEX
    Explanations

    throughout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نړۍ
    0.40
    今は
    0.40
     січня
    0.37
    odnik
    0.36
     ফেলেছেন
    0.35
     someday
    0.34
    ensureEqual
    0.33
    ⺈
    0.32
    ու
    0.32
     의한
    0.32
    POSITIVE LOGITS
     throughout
    4.13
     Throughout
    3.75
    Throughout
    3.72
    ตลอด
    2.84
     sepanjang
    2.78
     suốt
    2.42
     THRO
    2.38
     протяжении
    2.11
     boyunca
    1.95
     протягом
    1.91
    Act Density 0.099%

    No Known Activations