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

    Neuronpedia

    INDEX
    Explanations

    save

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    师
    -0.07
    ditor
    -0.07
    N
    -0.07
    认知
    -0.07
    ه
    -0.07
    styleType
    -0.07
     Teddy
    -0.07
    התפתחות
    -0.07
    holder
    -0.07
    ETO
    -0.07
    POSITIVE LOGITS
    起来了
    0.08
    十四
    0.07
     withdrawals
    0.07
    创立
    0.07
    	It
    0.07
    抽出
    0.07
     추
    0.07
     discontent
    0.07
     breathtaking
    0.07
    妩
    0.07
    Act Density 0.015%

    No Known Activations