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

    Neuronpedia

    INDEX
    Explanations

    code/application development

    np_max-act · gemini-2.0-flash

    the neuron activates on tokens that are compound identifiers containing hyphens (e.g. application or domain names like “my-old-app” or “google-music”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     offend
    -0.06
    ğini
    -0.06
    됨
    -0.06
    uilt
    -0.06
    图
    -0.06
     içeri
    -0.06
     shown
    -0.06
    شتر
    -0.06
     дет
    -0.06
    サイズ
    -0.06
    POSITIVE LOGITS
     OCD
    0.07
     GestureDetector
    0.07
     Moder
    0.06
     Name
    0.06
    aux
    0.06
     }];↵
    0.06
    	initialize
    0.06
     Lod
    0.06
     Abed
    0.06
     LIC
    0.06
    Act Density 0.050%

    No Known Activations