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

    Neuronpedia

    INDEX
    Explanations

    execution time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arguments
    0.36
     Kün
    0.36
    rox
    0.35
    mnf
    0.34
    ouden
    0.33
     chains
    0.33
    пта
    0.33
    ッキ
    0.33
    गुन
    0.33
     Už
    0.32
    POSITIVE LOGITS
     облада
    0.50
     poseen
    0.42
    靕
    0.42
    带动
    0.41
     posiad
    0.41
     possessing
    0.40
     Carrier
    0.40
    нё
    0.39
    яв
    0.39
     हूं
    0.39
    Act Density 0.016%

    No Known Activations