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

    Neuronpedia

    INDEX
    Explanations

    management/coding/databases

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens naming software‐type systems or projects (e.g. “management,” “system,” “aggregator,” “app”), i.e. when a document mentions a software project name or category.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    νας
    -0.08
     NES
    -0.07
    CONT
    -0.06
     ECB
    -0.06
     refining
    -0.06
     likeness
    -0.06
     Coff
    -0.06
    emacs
    -0.06
     Colonial
    -0.06
    CREASE
    -0.06
    POSITIVE LOGITS
     ");↵↵
    0.07
    ールド
    0.07
     приб
    0.06
    ">{
    0.06
    }")]↵
    0.06
     boost
    0.06
    ollect
    0.06
     */
↵
↵
    0.06
     इतन
    0.06
     lu
    0.06
    Act Density 0.091%

    No Known Activations