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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    The neuron primarily detects occurrences of the word “for” in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (di
    -0.06
     PSD
    -0.06
    META
    -0.06
    _rc
    -0.06
    pios
    -0.06
     Bei
    -0.06
     Harvey
    -0.06
    ahi
    -0.06
    anking
    -0.06
    _lt
    -0.06
    POSITIVE LOGITS
     profitability
    0.07
     clearly
    0.06
    <GameObject
    0.06
    	entity
    0.06
     Partisi
    0.06
    zend
    0.06
    erseniz
    0.06
    _pages
    0.06
     detached
    0.06
     Clearly
    0.06
    Act Density 0.090%

    No Known Activations