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

    Neuronpedia

    INDEX
    Explanations

    dimension

    np_max-act · gemini-2.0-flash

    The neuron specifically detects mentions of the word “dimension” (including its subword forms like “dimensionality,” “dimensionally,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ou
    -0.07
    boat
    -0.06
    	So
    -0.06
    _combo
    -0.06
     可
    -0.06
     Poe
    -0.06
    698
    -0.06
     Ho
    -0.06
     ya
    -0.06
    929
    -0.06
    POSITIVE LOGITS
     dimension
    0.14
     Dimension
    0.13
     dimensions
    0.13
    dimension
    0.12
     Dimensions
    0.11
    Dimension
    0.11
    _dimension
    0.10
    dimensions
    0.09
    Dimensions
    0.09
    imension
    0.09
    Act Density 0.013%

    No Known Activations