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

    Neuronpedia

    INDEX
    Explanations

    but followed by contrast or elaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.66
    ে
    0.65
    ه
    0.61
    '
    0.60
    k
    0.57
    ’
    0.55
    li
    0.53
    os
    0.52
    с
    0.50
     spree
    0.49
    POSITIVE LOGITS
     nein
    0.84
     illetve
    0.81
     Zusätzlich
    0.80
    ﺎ
    0.78
     käyttää
    0.76
     andere
    0.76
     imassa
    0.75
     yattha
    0.75
     zusätzliche
    0.74
     สืบค้นเมื่อ
    0.74
    Act Density 0.427%

    No Known Activations