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

    Neuronpedia

    INDEX
    Explanations

    In phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    K
    0.57
     czł
    0.53
    ే
    0.51
    ти
    0.49
    al
    0.48
    ्वती
    0.46
     XPath
    0.46
     János
    0.46
     uczni
    0.45
     HDD
    0.45
    POSITIVE LOGITS
    0.61
    ?
    0.57
    هم
    0.54
    이다
    0.52
    ни
    0.52
    сть
    0.50
    \
    0.49
    のは
    0.48
    ю
    0.48
    いる
    0.47
    Act Density 0.159%

    No Known Activations