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

    Neuronpedia

    INDEX
    Explanations

    varied topics and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    …"
    -0.06
       
    -0.06
     венти
    -0.06
     따라
    -0.06
     underline
    -0.06
     animated
    -0.06
     tên
    -0.06
    !"
    -0.06
    eed
    -0.06
    apot
    -0.06
    POSITIVE LOGITS
    ="")↵
    0.06
    	panic
    0.06
     disregard
    0.06
     ＜
    0.06
    Ark
    0.06
    enco
    0.06
     experimentation
    0.06
    FromClass
    0.06
    ))),↵
    0.06
    ,bool
    0.06
    Act Density 0.475%

    No Known Activations