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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to mathematical expressions

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

    LaTeX math commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -1.10
    parsedMessage
    -1.09
    Personendaten
    -1.08
    GEBURTSDATUM
    -1.08
     propOrder
    -0.99
    adaptiveStyles
    -0.99
     utafitiHapana
    -0.95
    OGND
    -0.95
    expandindo
    -0.95
    ConstraintMaker
    -0.94
    POSITIVE LOGITS
    ↵↵
    0.39
    The
    0.36
     The
    0.34
    //
    0.33
     //
    0.32
     the
    0.31
    hline
    0.31
    ↵
    0.29
    :
    0.28
        
    0.27
    Act Density 0.015%

    No Known Activations