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

    Neuronpedia

    INDEX
    Explanations

    fff white ;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    খা
    0.46
     havent
    0.45
    مع
    0.43
    рованные
    0.42
    omponent
    0.41
     supernatant
    0.40
    㳚
    0.40
    有害
    0.39
    中有
    0.39
    䣷
    0.39
    POSITIVE LOGITS
     B
    0.44
    Datei
    0.40
    Artificial
    0.38
     Prod
    0.38
     W
    0.38
     It
    0.38
    iment
    0.38
     artificial
    0.37
     Arn
    0.37
    ታት
    0.37
    Act Density 0.003%

    No Known Activations