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

    Neuronpedia

    INDEX
    Explanations

    documenting topics and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varit
    0.45
     หยุด
    0.42
     pyr
    0.41
     geometri
    0.41
     cancé
    0.41
     arbet
    0.40
     동물
    0.40
     magnes
    0.40
    RefManager
    0.40
    อุ
    0.40
    POSITIVE LOGITS
     interactions
    0.47
    Τα
    0.47
    interactions
    0.46
    याम
    0.45
     حساب
    0.44
    每一
    0.44
    Пер
    0.43
    互動
    0.43
    你可以
    0.42
    ósito
    0.42
    Act Density 0.002%

    No Known Activations