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

    Neuronpedia

    INDEX
    Explanations

    years and centuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    های
    0.58
    രോ
    0.57
    礫
    0.56
    breath
    0.56
    ίων
    0.53
     explo
    0.52
    ların
    0.52
    ه‌ی
    0.52
    ணும்
    0.51
    ケート
    0.51
    POSITIVE LOGITS
    ️⃣
    1.32
    ⃣
    1.31
    nd
    1.22
    0
    1.19
    ০
    1.07
    ″]
    1.05
    ″
    1.04
    ૦
    1.01
    9
    0.99
    ﻠ
    0.98
    Act Density 0.318%

    No Known Activations