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

    Neuronpedia

    INDEX
    Explanations

    step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্যস্ত
    0.46
    初步
    0.46
     vías
    0.43
     prélim
    0.42
     esbo
    0.41
    ដែរ
    0.40
     twofold
    0.39
     threefold
    0.39
    funcs
    0.39
    ingham
    0.39
    POSITIVE LOGITS
     Step
    0.60
     Schritt
    0.58
     step
    0.57
     Slowly
    0.56
    逐步
    0.54
    Step
    0.50
     slowly
    0.50
     STEP
    0.50
     langsam
    0.48
     шаг
    0.47
    Act Density 0.008%

    No Known Activations