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

    Neuronpedia

    INDEX
    Explanations

    more commonly or widely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.46
    america
    0.42
    دود
    0.41
    这时候
    0.40
    তরাং
    0.39
    র্প
    0.39
    anner
    0.39
    ACT
    0.38
    很好的
    0.38
    SON
    0.38
    POSITIVE LOGITS
     அதிச
    0.48
    ką
    0.47
    वेळी
    0.47
    ел
    0.47
    ﺔ
    0.46
     ውጤ
    0.46
     unmistak
    0.45
    tze
    0.45
     содержимое
    0.44
     Проци
    0.44
    Act Density 0.001%

    No Known Activations