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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Samples
    -0.07
    }&
    -0.07
    pearance
    -0.07
    [name
    -0.07
    LIKELY
    -0.06
    Sum
    -0.06
    New
    -0.06
    indows
    -0.06
     vehicles
    -0.06
    	level
    -0.06
    POSITIVE LOGITS
     gums
    0.07
     chống
    0.07
    NullOr
    0.06
    ́c
    0.06
     chân
    0.06
    舒
    0.06
     chứ
    0.06
     szcz
    0.06
    �a
    0.06
     fallout
    0.06
    Act Density 0.001%

    No Known Activations