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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash

    The neuron fires on contracted and modal/hedging words (e.g. “It’s,” “Sorry,” “must,” “I’m,” “don’t”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    astro
    -0.06
    (Tree
    -0.06
    顔
    -0.06
     unseren
    -0.06
    .AppendFormat
    -0.06
    urent
    -0.06
     prerequisites
    -0.06
    	flash
    -0.06
    536
    -0.06
     Towers
    -0.06
    POSITIVE LOGITS
     الجن
    0.08
     UNION
    0.07
    检
    0.07
    .'
    0.06
     ka
    0.06
     nok
    0.06
    _nome
    0.06
     succesfully
    0.06
     �
    0.06
     hiểm
    0.06
    Act Density 0.148%

    No Known Activations