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

    Neuronpedia

    INDEX
    Explanations

    responding to instructions and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ("",
    1.19
    /;
    1.12
    ?;
    1.11
     संधी
    1.08
    ,//
    1.07
     然后
    1.05
     vermel
    1.03
    *;
    1.02
     (),
    1.00
     ショルダー
    1.00
    POSITIVE LOGITS
    🆗
    0.91
    🆙
    0.91
    रासायनिक
    0.88
    ၉
    0.86
    😊
    0.86
     siitä
    0.86
    🔭
    0.85
    ँव
    0.85
    ၅
    0.84
    much
    0.84
    Act Density 0.040%

    No Known Activations