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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash

    This neuron fires on BEM-style double-underscore separators (the “__” in class names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (TEXT
    -0.06
     κορ
    -0.06
     matrices
    -0.06
     SSD
    -0.06
     vůči
    -0.06
    _events
    -0.06
     MADE
    -0.06
    _struct
    -0.06
    (duration
    -0.06
     convoy
    -0.06
    POSITIVE LOGITS
    cube
    0.09
    йн
    0.07
     WhatsApp
    0.07
    bestos
    0.07
    odoxy
    0.07
    -output
    0.06
     Indo
    0.06
     інтер
    0.06
     Comple
    0.06
    Workspace
    0.06
    Act Density 0.027%

    No Known Activations