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

    Neuronpedia

    INDEX
    Explanations

    issues after prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.25
    ，
    0.19
     Ако
    0.18
    ;
    0.18
    *
    0.17
     ،
    0.17
     ако
    0.17
    ↵
    0.17
     protéines
    0.17
    ）
    0.17
    POSITIVE LOGITS
     blatant
    0.24
     gradual
    0.23
     widespread
    0.22
     rampant
    0.21
     reliance
    0.20
     frequent
    0.19
     skewed
    0.19
     breakdowns
    0.19
     anonymity
    0.19
     बढ़ती
    0.19
    Act Density 0.891%

    No Known Activations