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

    Neuronpedia

    INDEX
    Explanations

    methods perescapismchapter importanceyoucoworker tone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    0.51
    教育
    0.45
     Educação
    0.41
     Transforming
    0.41
     notebooks
    0.40
     Ubuy
    0.40
     nud
    0.40
    フラー
    0.40
     Philosophy
    0.40
     Educ
    0.39
    POSITIVE LOGITS
    ۰
    0.53
    GSM
    0.51
    য়ান
    0.48
    ى
    0.46
     posibil
    0.46
     וכ
    0.45
    ர்ஸ்
    0.44
    Dtls
    0.43
    ListArr
    0.43
    Stocks
    0.43
    Act Density 0.001%

    No Known Activations