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

    Neuronpedia

    INDEX
    Explanations

    numbers and code

    np_max-act · gemini-2.0-flash

    This neuron activates on the token “US,” i.e. it flags mentions of “US” in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ACT
    -0.06
     HEX
    -0.06
    HTTPHeader
    -0.06
     shar
    -0.06
     arrests
    -0.06
    _Show
    -0.06
    relay
    -0.06
     Kickstarter
    -0.06
     furry
    -0.06
    _USED
    -0.06
    POSITIVE LOGITS
    odule
    0.07
     Dresden
    0.07
     Memory
    0.06
     nije
    0.06
     sitesinde
    0.06
     complaints
    0.06
     são
    0.06
    esp
    0.06
    100
    0.06
     volcan
    0.06
    Act Density 0.016%

    No Known Activations