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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting indicators in coding contexts

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

    javadoc and code configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BrowserModule
    -0.37
     BrowserModule
    -0.34
    Aiheesta
    -0.33
    anément
    -0.33
    argout
    -0.32
     cend
    -0.31
    BaseAdapter
    -0.31
     cq
    -0.31
    gree
    -0.31
    πως
    -0.31
    POSITIVE LOGITS
    ](#
    0.86
    #
    0.83
     #
    0.82
    /#
    0.77
     \#
    0.69
    \#
    0.68
     '#
    0.67
    /#/
    0.66
     $\#
    0.66
    +#
    0.66
    Act Density 0.112%

    No Known Activations