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

    Neuronpedia

    INDEX
    Explanations

    general chemistry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.75
    지
    0.71
    ต์
    0.63
     contralateral
    0.63
     titik
    0.60
    Վ
    0.60
    いた
    0.59
     สิ่ง
    0.59
    യാ
    0.59
     คลิป
    0.59
    POSITIVE LOGITS
    and
    1.02
    ين
    0.94
    ים
    0.89
    y
    0.88
    re
    0.85
    ok
    0.80
    يں
    0.80
    ámenes
    0.79
    হীন
    0.76
    ينا
    0.76
    Act Density 0.001%

    No Known Activations