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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash

    This neuron detects the asterisk symbols used as footnote or citation markers in legal documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    discard
    -0.07
     tóc
    -0.07
    intr
    -0.06
    ุ่
    -0.06
    .manage
    -0.06
     wishlist
    -0.06
    (cf
    -0.06
    Obama
    -0.06
    strcpy
    -0.06
    ISH
    -0.06
    POSITIVE LOGITS
     stiff
    0.07
     Dick
    0.07
    Mu
    0.06
     Lady
    0.06
     rosa
    0.06
    ereg
    0.06
    Genesis
    0.06
    .RequestParam
    0.06
     Katrina
    0.06
    pecific
    0.06
    Act Density 0.001%

    No Known Activations