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

    Neuronpedia

    INDEX
    Explanations

    keywords related to scientific terminology and data representations

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

    two or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.57
     surla
    -0.56
     informée
    -0.55
    دانشنامهٔ
    -0.54
    uxxxx
    -0.54
    脚注の使い方
    -0.50
     Италијани
    -0.47
    Ответить
    -0.47
    rrggbb
    -0.46
     CURIAM
    -0.45
    POSITIVE LOGITS
    这两个
    0.42
    这两
    0.36
    two
    0.34
    Ded
    0.33
    These
    0.32
     These
    0.32
     useSelector
    0.31
    Composable
    0.31
    Soorten
    0.30
    시
    0.30
    Act Density 0.145%

    No Known Activations