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

    Neuronpedia

    INDEX
    Explanations

    following a period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     culturais
    0.70
     capitalismo
    0.64
     tutela
    0.61
     weddings
    0.58
     kulttu
    0.57
    leriyle
    0.57
     utopian
    0.56
    ीत
    0.55
     capitalism
    0.55
     culturales
    0.55
    POSITIVE LOGITS
     but
    0.79
     However
    0.77
    However
    0.73
     поэтому
    0.72
     jedoch
    0.71
     however
    0.71
    ご確認ください
    0.68
     HOWEVER
    0.68
    Take
    0.67
     nhưng
    0.67
    Act Density 0.495%

    No Known Activations