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

    Neuronpedia

    INDEX
    Explanations

    substitute or replace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hani
    -0.08
    -animation
    -0.07
    (hWnd
    -0.07
    hy
    -0.06
     Mask
    -0.06
    _markers
    -0.06
    uru
    -0.06
    uration
    -0.06
    enna
    -0.06
     Patterns
    -0.06
    POSITIVE LOGITS
     Ś
    0.08
     Declaration
    0.07
     obliged
    0.06
     št
    0.06
    ].↵↵
    0.06
    _notes
    0.06
     Dort
    0.06
     ');↵
    0.06
     применения
    0.06
     Durch
    0.06
    Act Density 0.034%

    No Known Activations