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

    Neuronpedia

    INDEX
    Explanations

    cross the / times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.63
     обнов
    0.55
    ية
    0.54
    ا
    0.51
     attaque
    0.50
     oftent
    0.50
    ल
    0.49
     obliterated
    0.48
     ascent
    0.48
     embodying
    0.48
    POSITIVE LOGITS
     cross
    1.38
    交叉
    1.34
    cross
    1.24
    Cross
    1.20
     Cross
    1.18
     crosses
    1.13
     crossed
    1.12
     CROSS
    1.11
     क्रॉस
    1.10
     crossing
    1.06
    Act Density 0.020%

    No Known Activations