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

    Neuronpedia

    INDEX
    Explanations

    adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Meeting
    -0.06
     (("
    -0.06
    ть
    -0.06
    .flex
    -0.06
    тие
    -0.06
     다양한
    -0.06
    (mode
    -0.06
    )],↵
    -0.06
     nodeName
    -0.06
     Decoder
    -0.06
    POSITIVE LOGITS
    ちゃん
    0.07
     δεν
    0.06
     العق
    0.06
     burgers
    0.06
     یاد
    0.06
     پس
    0.06
     πρώ
    0.06
     critics
    0.06
    Personally
    0.06
     наст
    0.06
    Act Density 0.028%

    No Known Activations