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

    Neuronpedia

    INDEX
    Explanations

    growth conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     artificially
    0.56
     extraction
    0.52
     experimental
    0.51
     synthetic
    0.50
     artificial
    0.49
     induces
    0.48
     extracted
    0.48
     insoluble
    0.48
     using
    0.47
     aqueous
    0.46
    POSITIVE LOGITS
     یقینی
    0.48
     Parenting
    0.46
    竴
    0.46
     Chủ
    0.46
     Policing
    0.46
     继续
    0.45
     Entertain
    0.45
    祸
    0.43
    Contin
    0.43
    それぞれ
    0.43
    Act Density 0.010%

    No Known Activations