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

    Neuronpedia

    INDEX
    Explanations

    roman numerals and classifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementGuid
    0.41
     কিন্তু
    0.40
    istiche
    0.39
    攻擊
    0.39
    ônio
    0.38
    Rp
    0.38
    洷
    0.38
    <unused640>
    0.37
    codigo
    0.37
    Offering
    0.37
    POSITIVE LOGITS
     III
    0.86
     II
    0.73
    III
    0.70
     IV
    0.65
     VII
    0.62
    Ⅲ
    0.56
     VI
    0.55
     VIII
    0.54
    Ⅰ
    0.53
    Ⅳ
    0.50
    Act Density 0.043%

    No Known Activations