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

    Neuronpedia

    INDEX
    Explanations

    specific word pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دوم
    0.51
     Dom
    0.49
     أهم
    0.47
     Dominguez
    0.47
     لكن
    0.46
     बढ़त
    0.46
     কিন্তু
    0.44
     цик
    0.44
     nhưng
    0.43
     FSB
    0.43
    POSITIVE LOGITS
    s
    0.52
    m
    0.52
    ახებ
    0.49
    법
    0.49
     excav
    0.48
     artworks
    0.47
    ก
    0.47
    ෞ
    0.45
    ルト
    0.45
    boxing
    0.45
    Act Density 0.000%

    No Known Activations