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

    Neuronpedia

    INDEX
    Explanations

    security and text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    が高い
    0.43
    强大
    0.41
     Marketing
    0.41
     शा
    0.40
     शै
    0.39
    が高
    0.38
     marketing
    0.37
     b
    0.36
     hardware
    0.36
    Marketing
    0.36
    POSITIVE LOGITS
    WAYS
    0.42
    ély
    0.42
     Regal
    0.40
    lymp
    0.39
     Carpathians
    0.39
     selanjutnya
    0.39
    вано
    0.39
    pley
    0.38
     násled
    0.38
     ………………………………..
    0.37
    Act Density 0.000%

    No Known Activations