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

    Neuronpedia

    INDEX
    Explanations

    emphasis and sincerity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ương
    0.51
    骈
    0.49
    stimulation
    0.47
    ζ
    0.46
    дела
    0.45
    separator
    0.45
     jezika
    0.44
    scissor
    0.44
    Zh
    0.44
    俔
    0.43
    POSITIVE LOGITS
     genuinely
    0.78
     honestly
    0.63
     echt
    0.60
    Honestly
    0.57
    真的
    0.55
     REALLY
    0.54
     virkelig
    0.54
     genu
    0.54
     sincerely
    0.54
    是真的
    0.52
    Act Density 0.062%

    No Known Activations