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

    Neuronpedia

    INDEX
    Explanations

    across

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on occurrences of the preposition “across,” marking descriptions of distribution or extent.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    let
    -0.08
    	let
    -0.08
     bet
    -0.08
     Jul
    -0.08
     let
    -0.08
    jl
    -0.07
    Let
    -0.07
     gul
    -0.07
    "Well
    -0.07
    jd
    -0.07
    POSITIVE LOGITS
     across
    0.14
     Across
    0.12
    Across
    0.10
     Capt
    0.08
    :
    0.08
    exus
    0.08
    cross
    0.08
    ACE
    0.07
     ASC
    0.07
    AX
    0.07
    Act Density 0.018%

    No Known Activations