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

    Neuronpedia

    INDEX
    Explanations

    model response initiator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yeah
    0.69
     ah
    0.68
    넹
    0.66
    Hey
    0.66
    Yeah
    0.65
    嗯
    0.65
    سور
    0.65
    Yep
    0.65
     عمومی
    0.63
    hello
    0.63
    POSITIVE LOGITS
    аны
    0.63
     ###
    0.62
     ##
    0.61
    ##
    0.61
    કસ
    0.60
    भीर
    0.59
    bts
    0.58
    bure
    0.57
     Witten
    0.57
    郁
    0.55
    Act Density 0.399%

    No Known Activations