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

    Neuronpedia

    INDEX
    Explanations

    asking for guidance how to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ៖
    0.77
     grotes
    0.61
    :";
    0.58
     পেয়েছে
    0.57
     hvert
    0.56
    انہوں
    0.55
     mỗi
    0.55
    »:
    0.55
     каждую
    0.55
     desec
    0.54
    POSITIVE LOGITS
    我可以
    0.80
    if
    0.77
     يمكن
    0.73
    可以
    0.70
    would
    0.70
     posso
    0.69
     मैं
    0.66
     હું
    0.66
    应该
    0.66
    如果
    0.64
    Act Density 0.005%

    No Known Activations