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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uncompressed
    -0.07
    将
    -0.07
    MouseButton
    -0.06
     bundan
    -0.06
    。那
    -0.06
    _CLEAR
    -0.06
     }),
    -0.06
    �
    -0.06
    -available
    -0.06
    _figure
    -0.06
    POSITIVE LOGITS
     skate
    0.06
     shake
    0.06
    [min
    0.06
    เคร
    0.06
     fot
    0.06
    476
    0.06
    369
    0.06
     exerc
    0.06
    ераль
    0.06
    że
    0.06
    Act Density 0.000%

    No Known Activations