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

    Neuronpedia

    INDEX
    Explanations

    multilingual technology terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.41
    if
    0.38
     In
    0.38
    0.38
    ang
    0.37
    iation
    0.37
     B
    0.35
     in
    0.34
     Relationship
    0.33
     s
    0.33
    POSITIVE LOGITS
    ⵕ
    0.41
    蓝牙
    0.39
    ⵙ
    0.39
    を楽しむ
    0.38
     ایپ
    0.37
    バッテリー
    0.37
     muziek
    0.37
    ⴼ
    0.36
    BtnFill
    0.36
    音乐
    0.36
    Act Density 0.000%

    No Known Activations