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

    Neuronpedia

    INDEX
    Explanations

    Software configuration/disabling

    np_max-act · gemini-2.0-flash

    The neuron fires on build‐system configuration flags (e.g. CMake “-D…” options and “--disable/--enable” switches).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    日期
    -0.07
    total
    -0.07
    _logout
    -0.06
    /sidebar
    -0.06
    ction
    -0.06
     vine
    -0.06
    .myapplication
    -0.06
    하신
    -0.06
    ()
↵
    -0.06
     manifest
    -0.06
    POSITIVE LOGITS
     remarkably
    0.06
    -Ass
    0.06
    加工
    0.06
     Durch
    0.06
     pense
    0.06
     Fres
    0.06
     lasted
    0.06
    .Pull
    0.06
     stimulus
    0.06
    ='{$
    0.06
    Act Density 0.008%

    No Known Activations