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

    Neuronpedia

    INDEX
    Explanations

    provides a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وعلى
    1.34
     pusieron
    1.30
    то
    1.30
    ре
    1.26
    יא
    1.21
    А
    1.21
     démontrer
    1.20
    ల
    1.19
    ς
    1.18
     anunci
    1.16
    POSITIVE LOGITS
    o
    1.17
     salvaged
    1.11
    sc
    1.05
     hearted
    1.05
     synergies
    1.04
     ambit
    1.03
    มากมาย
    1.02
    th
    1.00
    liners
    1.00
    ਹੀਂ
    0.97
    Act Density 0.177%

    No Known Activations