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

    Neuronpedia

    INDEX
    Explanations

    If you have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     little
    0.95
    谓
    0.88
    aksud
    0.83
    ciri
    0.83
     paljon
    0.83
    ﻚ
    0.82
    ラム
    0.82
    时候
    0.81
    hört
    0.80
    言って
    0.79
    POSITIVE LOGITS
     GMO
    1.16
     ป
    1.15
     utilizando
    1.14
     dataset
    1.14
     investigador
    1.13
    𝒈
    1.11
     ٹینس
    1.10
     SSA
    1.09
     UVA
    1.08
     ú
    1.07
    Act Density 0.000%

    No Known Activations