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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on code import or include directives (e.g. lines starting with “import” in Java or “#include” in C/C++).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    NX
    -0.08
    worked
    -0.07
    Fields
    -0.07
    俗
    -0.07
    ，则
    -0.06
    ById
    -0.06
    ủa
    -0.06
    谓
    -0.06
     starring
    -0.06
    ADDR
    -0.06
    POSITIVE LOGITS
    .VISIBLE
    0.06
     Cree
    0.06
     Strategy
    0.06
     Dodge
    0.06
    _Err
    0.06
    +'</
    0.06
    ―
    0.06
     $$$
    0.06
     standards
    0.06
     culpa
    0.06
    Act Density 0.044%

    No Known Activations