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

    Neuronpedia

    INDEX
    Explanations

    Categories and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ================================================
    -0.07
    native
    -0.06
    ống
    -0.06
    	printf
    -0.06
     помог
    -0.06
     اصول
    -0.06
     获取
    -0.06
    Get
    -0.06
    Phoenix
    -0.06
     Numero
    -0.06
    POSITIVE LOGITS
    /car
    0.07
     luck
    0.07
     guessed
    0.07
    quences
    0.07
    _k
    0.06
     jar
    0.06
     surprise
    0.06
    .List
    0.06
     List
    0.06
     stir
    0.06
    Act Density 0.003%

    No Known Activations