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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations

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

    LaTeX math mode ^{\prime}

    np_acts-logits-general · gemini-2.0-flash

    prime numbers and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.61
    Istorija
    -0.58
    ibouti
    -0.55
     Про
    -0.55
     Ro
    -0.54
    stateMutability
    -0.53
    %)$
    -0.53
     tiết
    -0.53
    年
    -0.53
    teu
    -0.51
    POSITIVE LOGITS
    prime
    1.05
    ładka
    0.64
     évêque
    0.61
     prime
    0.60
    Prí
    0.57
     pascua
    0.57
     chré
    0.56
    ennium
    0.56
    Prime
    0.56
    )^{\
    0.55
    Act Density 0.238%

    No Known Activations