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

    Neuronpedia

    INDEX
    Explanations

    percentages and numerical data related to statistical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    50% of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saurait
    -0.49
     abstrato
    -0.44
    creva
    -0.43
     zprá
    -0.43
     aguja
    -0.42
     Grafen
    -0.41
     eût
    -0.41
     proprement
    -0.40
    SharedDtor
    -0.39
     étranger
    -0.39
    POSITIVE LOGITS
     Hälfte
    0.72
    half
    0.66
     Half
    0.65
     half
    0.65
    一半
    0.63
    Half
    0.63
     moitié
    0.61
     mitad
    0.59
     helft
    0.57
     HALF
    0.56
    Act Density 0.062%

    No Known Activations