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

    Neuronpedia

    INDEX
    Explanations

    commits, waiting for, accuracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bunnies
    0.50
     torneo
    0.45
     presenceData
    0.44
    ेच्छा
    0.42
     níveis
    0.41
     livelli
    0.41
     gifs
    0.41
    쾺
    0.40
    🤺
    0.40
     Zeiten
    0.39
    POSITIVE LOGITS
    FAILED
    0.47
    턱
    0.40
     Relating
    0.40
     இறு
    0.38
     앞
    0.38
     failed
    0.38
    0.38
     FAIL
    0.38
     어린
    0.38
    頜
    0.37
    Act Density 0.001%

    No Known Activations