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

    Neuronpedia

    INDEX
    Explanations

    api calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Diet
    0.42
     lẫn
    0.40
     diet
    0.37
     Forbes
    0.36
     Fate
    0.36
     Bingo
    0.35
     Ctrl
    0.35
     lanterns
    0.35
     Capsule
    0.35
    绮
    0.35
    POSITIVE LOGITS
    𒉺
    0.52
    retryWrites
    0.49
     internation
    0.48
     경쟁
    0.47
    ieť
    0.47
    रोला
    0.46
    Jw
    0.46
    fromj
    0.45
     asserting
    0.45
     tulee
    0.45
    Act Density 0.001%

    No Known Activations