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

    Neuronpedia

    INDEX
    Explanations

    foreign characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gru
    0.49
    gub
    0.48
     ul
    0.47
     tuf
    0.46
    gx
    0.46
     sitcom
    0.46
     ditt
    0.44
     latach
    0.44
    aj
    0.44
    MktCap
    0.44
    POSITIVE LOGITS
    ر
    0.53
    ર
    0.52
    ன்
    0.48
    ન
    0.48
    ש
    0.48
    з
    0.47
    ра
    0.47
    ר
    0.46
    ବ
    0.46
    ਰ
    0.46
    Act Density 0.000%

    No Known Activations