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

    Neuronpedia

    INDEX
    Explanations

    empty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Width
    -0.07
     polish
    -0.06
    ५
    -0.06
    Either
    -0.06
     locom
    -0.06
    رده
    -0.06
    bserv
    -0.06
     bump
    -0.06
    _voltage
    -0.06
    .bad
    -0.06
    POSITIVE LOGITS
     DIR
    0.07
     AUT
    0.07
    ‐‐
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵
    0.06
     Sharon
    0.06
     knull
    0.06
     '');
    0.06
     Francie
    0.06
    _TMP
    0.06
    ,[],
    0.06
    Act Density 0.005%

    No Known Activations