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

    Neuronpedia

    INDEX
    Explanations

    's or '3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल्पनिक
    1.66
    வ
    1.54
    Վ
    1.43
    trajectory
    1.38
    с
    1.38
    стю
    1.37
    וד
    1.35
    образи
    1.33
    艋
    1.32
    𝓎
    1.32
    POSITIVE LOGITS
    an
    1.92
    عات
    1.59
     designate
    1.51
    aný
    1.46
    েশন
    1.45
    eer
    1.45
    ză
    1.44
    iselle
    1.41
     Vikt
    1.40
    ة
    1.40
    Act Density 0.123%

    No Known Activations