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

    Neuronpedia

    INDEX
    Explanations

    table summarizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consists
    0.84
     consisted
    0.83
    淘宝
    0.78
    िक
    0.76
     peas
    0.75
     consist
    0.75
    িক
    0.74
    נטי
    0.74
    ats
    0.74
    送料
    0.74
    POSITIVE LOGITS
     fixing
    0.69
     manifestazione
    0.66
     achievement
    0.64
     Fixed
    0.63
     seriousness
    0.61
     తెలిప
    0.61
     реализации
    0.61
    振り返
    0.60
     religione
    0.60
     выражения
    0.60
    Act Density 0.014%

    No Known Activations