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

    Neuronpedia

    INDEX
    Explanations

    expressions related to programming constructs or code snippets

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

    code or mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PYX
    -0.72
     '\\;'
    -0.71
     Vikipedi
    -0.57
    ksikon
    -0.52
    FunctionFlags
    -0.52
    oredCriteria
    -0.51
    TestingModule
    -0.51
    MigrationBuilder
    -0.47
    encodeWith
    -0.44
     transfieras
    -0.44
    POSITIVE LOGITS
     Administrativna
    0.48
    endregion
    0.47
    fromnode
    0.46
    +:+
    0.46
     autorytatywna
    0.42
     Paglinawan
    0.41
     <<<<<<<<<<<<<<
    0.40
    verifyException
    0.40
    NameInMap
    0.39
    帖最后由
    0.38
    Act Density 0.127%

    No Known Activations