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

    Neuronpedia

    INDEX
    Explanations

    or list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     achieves
    0.46
     queues
    0.46
     weaknesses
    0.43
    해야
    0.43
     해야
    0.41
     inhal
    0.41
     высокую
    0.41
     flam
    0.39
     violators
    0.39
     zvyš
    0.39
    POSITIVE LOGITS
     know
    0.87
     biết
    0.79
    know
    0.77
     знать
    0.69
    知道
    0.67
     understand
    0.64
    Know
    0.63
     Know
    0.61
    知
    0.61
     જાણ
    0.59
    Act Density 0.000%

    No Known Activations