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

    Neuronpedia

    INDEX
    Explanations

    cigarette and related context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    2.06
     торже
    1.95
    Вы
    1.91
     đỡ
    1.73
    وم
    1.68
     alcuna
    1.66
     certamente
    1.63
    굉장
    1.63
    д
    1.61
     одежда
    1.60
    POSITIVE LOGITS
    ש
    2.11
    laştır
    1.72
     worded
    1.68
    fu
    1.63
     myocytes
    1.63
     pys
    1.55
    ah
    1.54
    ھا
    1.52
    la
    1.51
    ھ
    1.51
    Act Density 0.001%

    No Known Activations