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

    Neuronpedia

    INDEX
    Explanations

    Scientific detection/analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     démocr
    -0.53
     trụ
    -0.51
     définiti
    -0.50
     fondament
    -0.48
    INCT
    -0.46
     mères
    -0.45
     fraî
    -0.45
     comprennent
    -0.45
     Tuch
    -0.45
     "":
    -0.45
    POSITIVE LOGITS
     GenerationType
    0.57
    MessageOf
    0.55
     HasFactory
    0.54
     slightest
    0.52
    addPreferredGap
    0.52
    Tembelea
    0.51
     Salim
    0.51
     архивлан
    0.49
     handleMessage
    0.49
    titleMargin
    0.48
    Act Density 0.004%

    No Known Activations