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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash

    This neuron detects terms from the standard opening description of a radio station (e.g. “a radio station,” “broadcasting,” format names, frequencies, ownership/serving-area metadata).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nozzle
    -0.06
     Wars
    -0.06
    ighthouse
    -0.06
    .Keyboard
    -0.06
    edores
    -0.06
     contested
    -0.06
    	required
    -0.06
     lạ
    -0.06
     hands
    -0.06
    orest
    -0.06
    POSITIVE LOGITS
    SPI
    0.07
     blues
    0.06
    __));↵
    0.06
     {...
    0.06
    	copy
    0.06
     ('\
    0.06
     smooth
    0.06
     fgets
    0.06
     categorie
    0.06
    (express
    0.06
    Act Density 0.004%

    No Known Activations