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

    Neuronpedia

    INDEX
    Explanations

    possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     olds
    -0.07
     допомоги
    -0.07
    냐
    -0.07
    세요
    -0.07
    (bits
    -0.06
     part
    -0.06
    orz
    -0.06
    атели
    -0.06
     vending
    -0.06
     know
    -0.06
    POSITIVE LOGITS
    episode
    0.07
    @Json
    0.06
     subpoena
    0.06
    zept
    0.06
    req
    0.06
    LEGRO
    0.06
    .orange
    0.06
    	UINT
    0.06
    idden
    0.06
     Дон
    0.05
    Act Density 0.022%

    No Known Activations