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

    Neuronpedia

    INDEX
    Explanations

    shows the or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     view
    0.47
     nazar
    0.46
     VFX
    0.46
    teau
    0.45
     propagand
    0.45
    สนามกีฬา
    0.45
     sacrifice
    0.44
     audiovis
    0.44
     zeal
    0.43
    的目标
    0.42
    POSITIVE LOGITS
     teh
    0.42
    các
    0.42
     an
    0.41
    лер
    0.39
     составе
    0.39
    top
    0.39
    раст
    0.39
     mindestens
    0.39
     how
    0.39
    அ
    0.39
    Act Density 0.004%

    No Known Activations