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

    Neuronpedia

    INDEX
    Explanations

    via, through, to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    össä
    0.78
     کرل
    0.77
     aportan
    0.76
     दायर
    0.74
     तुम्हारा
    0.73
     dSample
    0.73
     그렇
    0.70
     പറയ
    0.70
     살펴보
    0.70
    에서는
    0.70
    POSITIVE LOGITS
     kepada
    2.06
     via
    1.87
     στους
    1.54
     through
    1.43
    via
    1.40
     aos
    1.27
     melalui
    1.24
     along
    1.20
     Via
    1.20
     to
    1.19
    Act Density 0.456%

    No Known Activations