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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental methodologies and data structures

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

    technical or abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.38
    たしか
    -0.38
    ⎠
    -0.37
    罷
    -0.36
    Sklici
    -0.36
     indeed
    -0.36
     bym
    -0.35
    ently
    -0.34
    XSSF
    -0.34
     kekinian
    -0.34
    POSITIVE LOGITS
    ]=>
    0.60
     Italijanski
    0.59
     ویکی‌پدی
    0.52
    Спасылкі
    0.50
    resizingMask
    0.50
    Хьажоргаш
    0.49
     EconPapers
    0.47
    ieteur
    0.47
    тьяна
    0.47
    Дереккөздер
    0.46
    Act Density 0.202%

    No Known Activations