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

    Neuronpedia

    INDEX
    Explanations

    hex

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the word “hex,” signaling mentions of hexagonal (hex) grid contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    141
    -0.08
     DRIVER
    -0.07
    .imp
    -0.07
     Injury
    -0.07
    Skin
    -0.07
    �建
    -0.07
     Marvin
    -0.06
    ียนบ
    -0.06
    .driver
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Hex
    0.11
     Hex
    0.10
    hex
    0.10
     hex
    0.10
    (hex
    0.08
    .Hex
    0.08
     HEX
    0.07
     Buchanan
    0.07
    hash
    0.07
    _hex
    0.07
    Act Density 0.007%

    No Known Activations