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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ->
    -0.07
    Bean
    -0.07
    Rs
    -0.06
    -thinking
    -0.06
     Canterbury
    -0.06
    craft
    -0.06
     查询
    -0.06
    _il
    -0.06
     پرداخت
    -0.06
     tal
    -0.06
    POSITIVE LOGITS
    contenido
    0.07
    िभ
    0.06
    _sq
    0.06
    ερ
    0.06
    -->
↵
    0.06
     eskorte
    0.06
    	vec
    0.06
     numb
    0.06
    vecs
    0.06
     Ring
    0.06
    Act Density 0.082%

    No Known Activations