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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lucia
    -0.08
     endangered
    -0.07
    Criterion
    -0.07
     αυτά
    -0.07
     Password
    -0.07
     for
    -0.07
    .cpp
    -0.06
    /package
    -0.06
    џџџџ
    -0.06
     "↵
    -0.06
    POSITIVE LOGITS
    	position
    0.07
     кисл
    0.07
     Portions
    0.06
    َى
    0.06
       ↵    ↵
    0.06
    －
    0.06
    )((((
    0.06
     Hait
    0.06
     Μπ
    0.06
    _ARROW
    0.06
    Act Density 0.005%

    No Known Activations