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

    Neuronpedia

    INDEX
    Explanations

    human and existence concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    İ
    0.57
    Ка
    0.54
    ส
    0.52
    ת
    0.50
    Я
    0.50
    ה
    0.50
    ی
    0.49
    Б
    0.49
    Dü
    0.47
    มี
    0.47
    POSITIVE LOGITS
     calculado
    0.48
     keiner
    0.47
    yto
    0.47
    iums
    0.46
    зже
    0.46
     chewy
    0.46
     ພວກເຮົາ
    0.45
     თქვენ
    0.45
     څرنګوالی
    0.45
     emailed
    0.44
    Act Density 0.002%

    No Known Activations