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

    Neuronpedia

    INDEX
    Explanations

    documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Shown
    -0.07
    нош
    -0.07
     shaky
    -0.07
     včetně
    -0.06
     spectacular
    -0.06
    皮
    -0.06
     Titans
    -0.06
     getPath
    -0.06
     endors
    -0.06
     pog
    -0.06
    POSITIVE LOGITS
    :before
    0.06
    Fo
    0.06
    Plug
    0.06
    ónica
    0.06
    SUMER
    0.06
    .unknown
    0.06
     """",↵
    0.06
     gigg
    0.06
    탕
    0.06
     ys
    0.06
    Act Density 0.129%

    No Known Activations