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

    Neuronpedia

    INDEX
    Explanations

    aimed at or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elő
    0.54
     égard
    0.51
    த்துக்கும்
    0.49
    o
    0.49
    ენა
    0.47
     intérpre
    0.47
     MDLVertex
    0.47
     samano
    0.47
     privato
    0.46
     samego
    0.46
    POSITIVE LOGITS
     Sä
    0.50
    ים
    0.49
     globalization
    0.49
     نړۍ
    0.46
    С
    0.46
     Manufacturing
    0.46
    il
    0.46
    ات
    0.45
     Sales
    0.45
    Chuck
    0.45
    Act Density 0.000%

    No Known Activations