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

    Neuronpedia

    INDEX
    Explanations

    symbols following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    などは
    1.17
    等は
    1.10
    なども
    1.07
     etc
    0.98
    などに
    0.97
    etc
    0.96
     등이
    0.94
    等
    0.94
    などを
    0.93
     usw
    0.90
    POSITIVE LOGITS
    ™.
    1.44
    ®.
    1.43
    。
    1.37
    ¹.
    1.35
    **.
    1.32
    .
    1.27
    !.
    1.26
    !!.
    1.26
    ।
    1.26
    。.
    1.26
    Act Density 0.304%

    No Known Activations