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

    Neuronpedia

    INDEX
    Explanations

    module.exports patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗴
    1.15
     Breite
    1.13
    ال
    1.11
    ли
    1.07
    তু
    1.04
    अगर
    1.03
     activated
    1.01
    ième
    1.00
    це
    1.00
    Cheng
    0.97
    POSITIVE LOGITS
    ă
    1.12
    ीन
    1.11
     nesta
    1.11
    !\!\
    1.08
    nya
    1.07
    в
    1.06
     reng
    1.06
     pues
    1.04
    ीत
    1.03
    分解
    1.03
    Act Density 0.002%

    No Known Activations