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

    Neuronpedia

    INDEX
    Explanations

    cable

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “cable” (and its plural form) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sort
    -0.08
     произ
    -0.07
    ("--------------------------------
    -0.07
    Sort
    -0.07
    	UN
    -0.07
    .executor
    -0.07
     Millenn
    -0.07
    .INT
    -0.06
    .sprite
    -0.06
     egret
    -0.06
    POSITIVE LOGITS
     cable
    0.13
     cables
    0.12
     Cable
    0.10
    AML
    0.08
    bands
    0.08
     Capital
    0.08
    宙
    0.07
    cela
    0.07
    acle
    0.07
    battle
    0.07
    Act Density 0.004%

    No Known Activations