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

    Neuronpedia

    INDEX
    Explanations

    accent

    np_max-act · gemini-2.0-flash

    The neuron is triggered by function parameter names in JavaScript definitions (e.g. “uploadTasks” and “retry”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ationship
    -0.07
    len
    -0.06
     cheer
    -0.06
    Precision
    -0.06
    ondrous
    -0.06
    รษ
    -0.06
    орм
    -0.06
    cem
    -0.06
    _xyz
    -0.06
    idi
    -0.06
    POSITIVE LOGITS
     Türkçe
    0.08
    /router
    0.07
     {}.
    0.07
     LO
    0.07
     uomo
    0.06
    .b
    0.06
    ’.↵↵
    0.06
    .modelo
    0.06
     šť
    0.06
    (jQuery
    0.06
    Act Density 0.061%

    No Known Activations