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

    Neuronpedia

    INDEX
    Explanations

    individuals or authors referenced in academic or scientific contexts

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

    initials ending in period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.80
     queſta
    -0.73
     beſch
    -0.71
    ロウィン
    -0.69
     tartalomajánló
    -0.69
     Wikimedijinoj
    -0.69
    XmlAccessType
    -0.68
    Хьажоргаш
    -0.68
    <unused79>
    -0.67
    <unused6>
    -0.67
    POSITIVE LOGITS
     M
    0.51
     H
    0.50
     K
    0.49
     B
    0.49
    M
    0.47
     L
    0.47
    H
    0.46
     J
    0.45
     C
    0.45
    L
    0.45
    Act Density 0.057%

    No Known Activations