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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Colombian
    -0.06
     caching
    -0.06
     athletics
    -0.06
     midway
    -0.06
     coaster
    -0.06
    زد
    -0.06
     discipline
    -0.06
    (rules
    -0.06
    ingles
    -0.06
     resposta
    -0.06
    POSITIVE LOGITS
     UNUSED
    0.07
     JsonRequestBehavior
    0.06
    asz
    0.06
    باشد
    0.06
     toDate
    0.06
     تهران
    0.06
    	TokenName
    0.06
    940
    0.06
    	log
    0.06
    合格
    0.06
    Act Density 0.235%

    No Known Activations