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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash

    tools and resources related to system administration and management.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    Explanation of neuron 4 behavior: the main thing this neuron does is find hedging or disclaimer phrases (e.g. “not technically”) indicating exclusion.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     piş
    -0.07
    画
    -0.07
    IRA
    -0.07
     Ghost
    -0.06
    �
    -0.06
     Gand
    -0.06
    _patch
    -0.06
    Det
    -0.06
    κή
    -0.06
     Abbott
    -0.06
    POSITIVE LOGITS
    	writel
    0.06
    Normalized
    0.06
    _SUPPLY
    0.06
    užel
    0.06
    	retval
    0.06
    ptune
    0.06
     abol
    0.06
     Ukraj
    0.06
    .PropertyType
    0.06
     sliders
    0.06
    Act Density 0.073%

    No Known Activations