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

    Neuronpedia

    INDEX
    Explanations

    backslashes or escape characters commonly used in programming and mathematical notation

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

    end of turn marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.75
    Personendaten
    -0.73
    -0.69
    TagMode
    -0.64
    rrggbb
    -0.63
     queſta
    -0.60
    exitRule
    -0.60
     "");
    -0.58
    matchCondition
    -0.56
    aarrggbb
    -0.54
    POSITIVE LOGITS
    ↵↵
    0.44
    .
    0.43
     Comment
    0.41
    \
    0.41
     Comments
    0.39
     Rocket
    0.37
     root
    0.36
     Johnston
    0.36
     rocket
    0.36
     hiver
    0.35
    Act Density 0.001%

    No Known Activations