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

    Neuronpedia

    INDEX
    Explanations

    hello bot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ڈن
    0.43
     mesmos
    0.41
     abrang
    0.41
     erlä
    0.38
     yanı
    0.38
     tartalmaz
    0.37
    !='')
    0.37
     চৈত
    0.37
     )\
    0.37
     '_
    0.37
    POSITIVE LOGITS
    So
    0.68
     So
    0.64
    Okay
    0.59
     Okay
    0.53
     so
    0.52
    Guys
    0.52
    Arkadaşlar
    0.52
     okay
    0.52
    question
    0.51
     所以
    0.51
    Act Density 0.004%

    No Known Activations