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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prostu
    0.80
     reaping
    0.79
    慢慢
    0.75
     debuts
    0.74
     semuanya
    0.74
     goodies
    0.73
     melakukannya
    0.73
     énfasis
    0.72
     거지
    0.72
     tweaking
    0.71
    POSITIVE LOGITS
    Describe
    1.99
    What
    1.84
     Describe
    1.81
    Write
    1.77
    Explain
    1.72
     Write
    1.71
     What
    1.66
    Which
    1.66
     describe
    1.64
    Give
    1.58
    Act Density 1.159%

    No Known Activations