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

    Neuronpedia

    INDEX
    Explanations

    Maya, Angelina, Angel names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    心の
    0.66
    ریت
    0.63
     amni
    0.62
    тори
    0.61
     culp
    0.60
     angina
    0.59
     sumo
    0.59
     meringue
    0.58
     deja
    0.58
     renin
    0.58
    POSITIVE LOGITS
    _
    0.76
    ح
    0.65
    я
    0.58
    il
    0.57
    ik
    0.56
    ल
    0.56
    ہ
    0.54
    0
    0.51
    ش
    0.51
    Meeting
    0.50
    Act Density 0.000%

    No Known Activations