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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    X
    -0.08
    	namespace
    -0.07
    next
    -0.07
     görüyor
    -0.07
    Ya
    -0.07
    .GetData
    -0.07
    弟弟
    -0.07
    F
    -0.07
    经理
    -0.07
     ner
    -0.06
    POSITIVE LOGITS
    intern
    0.07
     Genuine
    0.07
    쵝
    0.07
    �
    0.07
    oppel
    0.07
    inati
    0.07
     główna
    0.07
    Ջ
    0.07
    iji
    0.06
    iotic
    0.06
    Act Density 0.008%

    No Known Activations