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

    Neuronpedia

    INDEX
    Explanations

    movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Voyager
    -0.07
    猊
    -0.07
    _mem
    -0.07
    DIR
    -0.07
     rehab
    -0.07
     Bachelor
    -0.07
     hemp
    -0.07
     raster
    -0.07
    믕
    -0.06
     Cyber
    -0.06
    POSITIVE LOGITS
    ('')↵
    0.08
    场合
    0.08
    꼴
    0.08
     ));↵↵
    0.08
    uting
    0.07
    ()
↵
↵
↵
    0.07
    ('');↵↵
    0.07
    raises
    0.07
    [];↵↵
    0.07
    ];↵↵
    0.07
    Act Density 0.034%

    No Known Activations