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

    Neuronpedia

    INDEX
    Explanations

    inquiries related to learning resources or tutorials

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

    courses and tutorials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.48
    +#+
    -0.44
     تضيفلها
    -0.42
    tangentMode
    -0.42
    GIVEREF
    -0.42
     Chwiliwch
    -0.39
    Personendaten
    -0.38
     fær
    -0.38
    nodoc
    -0.37
    RTEE
    -0.36
    POSITIVE LOGITS
    -------
    0.50
    出版年
    0.48
    AndEndTag
    0.47
    postsleuth
    0.46
    Демографія
    0.46
    קישורים
    0.45
    RegressionTest
    0.43
    escar
    0.43
    ocu
    0.43
     noDo
    0.42
    Act Density 0.051%

    No Known Activations