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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash

    The neuron fires on compiler/linker attributes and directives (e.g. export‐ and calling‐convention macros, pragmas, annotation tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ware
    -0.07
    -ROM
    -0.07
     Mandal
    -0.07
    DIV
    -0.06
     Owens
    -0.06
     течение
    -0.06
     prostitutas
    -0.06
     foes
    -0.06
     Elite
    -0.06
    (success
    -0.06
    POSITIVE LOGITS
    ็ด
    0.07
    elman
    0.07
     З
    0.07
    .single
    0.06
     시
    0.06
    想要
    0.06
    чает
    0.06
    _pg
    0.06
    NTAX
    0.06
     математи
    0.06
    Act Density 0.046%

    No Known Activations