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

    Neuronpedia

    INDEX
    Explanations

    Comparing groups in studies

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on terms used in reporting group comparisons and statistical results (e.g. “compared,” “with,” “controls,” numeric values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	bit
    -0.07
     Williams
    -0.07
     fines
    -0.07
    /company
    -0.06
    .me
    -0.06
    顔
    -0.06
     distur
    -0.06
     Shadows
    -0.06
     alarms
    -0.06
     فى
    -0.06
    POSITIVE LOGITS
    getSimpleName
    0.07
     공개
    0.06
    >()->
    0.06
     ла
    0.06
     syst
    0.06
     jogador
    0.06
    �
    0.06
    OVER
    0.06
    962
    0.06
    _joint
    0.06
    Act Density 0.039%

    No Known Activations