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

    Neuronpedia

    INDEX
    Explanations

    introductory adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    等の
    0.88
    などの
    0.88
     మాత్రమే
    0.86
    ?????
    0.86
    Write
    0.85
     등의
    0.81
     Ре
    0.80
    ieuse
    0.80
    ???
    0.78
     НЕ
    0.78
    POSITIVE LOGITS
     Frankly
    1.42
     Personally
    1.31
    Honestly
    1.30
    Personally
    1.30
     Honestly
    1.29
     Basically
    1.26
     Certainly
    1.25
     Interestingly
    1.18
     Alright
    1.16
     Essentially
    1.16
    Act Density 0.235%

    No Known Activations