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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.31
    yl
    0.30
    -
    0.28
    ang
    0.28
    fo
    0.28
    ť
    0.28
    fi
    0.27
    res
    0.27
     вроде
    0.26
     situasi
    0.26
    POSITIVE LOGITS
    টির
    0.34
     निखिल
    0.33
    രിയ
    0.30
     Nikhil
    0.30
     spel
    0.30
     itself
    0.28
     غور
    0.28
    টি
    0.28
     originale
    0.28
    を入力
    0.28
    Act Density 0.037%

    No Known Activations