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

    Neuronpedia

    INDEX
    Explanations

    collecting data from lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যাত্রা
    0.50
     तत्काल
    0.46
     fluctuates
    0.45
     került
    0.44
     колеба
    0.41
     комитета
    0.41
     funcionamiento
    0.41
    奋斗
    0.40
     fonctionnement
    0.39
     কারা
    0.39
    POSITIVE LOGITS
    寻找
    0.74
     seeking
    0.65
     mencari
    0.64
    一遍
    0.63
     buscando
    0.61
     trying
    0.57
    🚶
    0.53
     collecting
    0.49
    seeking
    0.49
     hoping
    0.48
    Act Density 0.026%

    No Known Activations