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

    Neuronpedia

    INDEX
    Explanations

    ostree remote refs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dequeue
    0.43
     기반
    0.42
     AI
    0.40
     आर्टिफिशियल
    0.39
    AI
    0.39
     Warhol
    0.39
    Dataset
    0.38
     باز
    0.38
     സമ്മ
    0.38
     പ്രശ്
    0.37
    POSITIVE LOGITS
     quotients
    0.41
    τας
    0.40
     للصف
    0.39
     currently
    0.39
    ithmetic
    0.38
     quotient
    0.38
    asin
    0.38
     homeschool
    0.38
    ন্তা
    0.37
    نة
    0.37
    Act Density 0.000%

    No Known Activations