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

    Neuronpedia

    INDEX
    Explanations

    harmful thoughts or urges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     permeates
    0.52
     vanishes
    0.46
     включает
    0.46
     является
    0.45
     encompasses
    0.44
     ہونا
    0.44
     применяется
    0.44
     itself
    0.43
     varies
    0.43
     disappears
    0.43
    POSITIVE LOGITS
     want
    0.98
     have
    0.97
    觉得
    0.90
    覺得
    0.84
     wanted
    0.79
     know
    0.79
     knew
    0.77
     merasa
    0.77
    have
    0.76
     feel
    0.73
    Act Density 0.015%

    No Known Activations