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

    Neuronpedia

    INDEX
    Explanations

    attempted to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     catalyzes
    0.39
     eignet
    0.39
    就可以了
    0.38
    ကြီး
    0.38
    抱怨
    0.37
     consumes
    0.36
     Learn
    0.36
     маъ
    0.36
     learn
    0.35
    Filename
    0.35
    POSITIVE LOGITS
     постара
    1.29
     سعی
    1.12
     tries
    1.11
     стара
    1.11
     trying
    1.09
     attempt
    1.08
     try
    1.07
     попыта
    1.07
     চেষ্টা
    1.06
     berusaha
    1.06
    Act Density 0.026%

    No Known Activations