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

    Neuronpedia

    INDEX
    Explanations

    simple explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comparación
    0.39
     quadr
    0.39
     replic
    0.39
    datad
    0.38
     duplicating
    0.38
    ozz
    0.37
     Mavericks
    0.36
     sho
    0.36
     replicating
    0.36
     பரப்பு
    0.36
    POSITIVE LOGITS
     Nay
    0.47
     سادہ
    0.47
     ساده
    0.43
     सिंपल
    0.42
     البسط
    0.42
    餬
    0.42
     Considerable
    0.42
     सिंपली
    0.41
    简
    0.40
     छोटे
    0.40
    Act Density 0.000%

    No Known Activations