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

    Neuronpedia

    INDEX
    Explanations

    programming and mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     настоящий
    1.19
     площади
    1.12
    স
    1.05
     pued
    1.04
    স্ব
    1.03
    没有
    1.03
    ৭
    1.02
     millones
    1.01
     দা
    1.00
    સ
    1.00
    POSITIVE LOGITS
    කි
    1.15
    ering
    1.06
    я
    1.03
    ena
    0.96
    he
    0.95
    akse
    0.94
    骥
    0.93
     Essa
    0.91
    שי
    0.90
    eah
    0.90
    Act Density 0.000%

    No Known Activations