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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associated formatting in a technical context

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

    numeric attribute values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.43
    アリ
    -0.38
     τη
    -0.38
     Oran
    -0.37
     tele
    -0.36
    Mire
    -0.36
     pla
    -0.35
     tel
    -0.35
     Mire
    -0.35
    orsese
    -0.34
    POSITIVE LOGITS
     zoude
    0.66
     AspNetCore
    0.61
     zijne
    0.61
     restantes
    0.56
     asupra
    0.56
     verantwoorde
    0.56
     kleding
    0.56
     conseguenze
    0.54
     gră
    0.54
     mijne
    0.53
    Act Density 0.375%

    No Known Activations