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

    Neuronpedia

    INDEX
    Explanations

    learned about events and stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    трите
    0.47
     announc
    0.43
     foto
    0.43
     telefon
    0.42
    طلب
    0.41
     evin
    0.41
     wifi
    0.41
     photos
    0.40
     distribu
    0.40
     necess
    0.40
    POSITIVE LOGITS
    Cyan
    0.55
    Bind
    0.51
    8
    0.49
    9
    0.47
    3
    0.46
    Car
    0.45
     Cyan
    0.45
    6
    0.45
    কে
    0.44
    Azure
    0.44
    Act Density 0.001%

    No Known Activations