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

    Neuronpedia

    INDEX
    Explanations

    "> tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whip
    0.54
     queue
    0.51
     whisk
    0.50
     huit
    0.50
     mez
    0.50
     canale
    0.49
     antidote
    0.48
     matrix
    0.47
     winner
    0.47
     swim
    0.46
    POSITIVE LOGITS
    ᆼ
    0.47
     இடம்பெ
    0.44
    论
    0.44
     เง
    0.43
     প্রত
    0.42
    䧺
    0.42
    ouml
    0.42
    己
    0.42
    ఏ
    0.42
     단순
    0.41
    Act Density 0.001%

    No Known Activations