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

    Neuronpedia

    INDEX
    Explanations

    state of being or independence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ჩატი
    0.60
     plików
    0.59
     کوډ
    0.57
     تلیفون
    0.57
     utilisez
    0.56
     бясплат
    0.54
     kullanıcı
    0.54
     deaktiv
    0.54
     кеңсе
    0.54
    dyž
    0.53
    POSITIVE LOGITS
     spiritual
    0.64
     postulates
    0.55
     Homo
    0.50
     духов
    0.49
     worldview
    0.49
     Spiritual
    0.48
     incompar
    0.48
     manifestations
    0.47
     upbringing
    0.47
    創造
    0.47
    Act Density 0.024%

    No Known Activations