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

    Neuronpedia

    INDEX
    Explanations

    radio

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of radio-astronomy terminology, especially the word “radio” (often in “radio jets”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .containsKey
    -0.07
     integerValue
    -0.06
    .NORTH
    -0.06
    .HasValue
    -0.06
    .Objects
    -0.06
    .deepcopy
    -0.06
     putas
    -0.06
    _Native
    -0.06
     расч
    -0.06
     hại
    -0.06
    POSITIVE LOGITS
     toen
    0.07
    ylon
    0.06
     abst
    0.06
     Fey
    0.06
    块
    0.06
     Eleven
    0.06
     implication
    0.06
     MÜ
    0.06
     resembles
    0.06
    ưới
    0.06
    Act Density 0.004%

    No Known Activations