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

    Neuronpedia

    INDEX
    Explanations

    detailed information and descriptions about specific studies or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following "of," "on," or "describe"

    np_acts-logits-general · gemini-2.0-flash

    how questions are asked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frågan
    -0.50
     financières
    -0.47
     cœurs
    -0.47
     larmes
    -0.45
    anterie
    -0.45
    urnum
    -0.44
    Herzliche
    -0.44
    amblea
    -0.44
    еремо
    -0.44
     Normdatei
    -0.44
    POSITIVE LOGITS
     how
    0.91
     cómo
    0.64
     what
    0.59
     مدى
    0.58
     bagaimana
    0.55
    how
    0.50
     nasıl
    0.49
     كيفية
    0.49
     كيف
    0.49
     hvordan
    0.45
    Act Density 0.538%

    No Known Activations