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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    جع
    -0.06
    --;↵
    -0.06
     habit
    -0.06
    _species
    -0.06
     criticizing
    -0.06
    ри
    -0.06
    .some
    -0.06
     Syria
    -0.06
    	Common
    -0.06
    Prof
    -0.06
    POSITIVE LOGITS
    _THAT
    0.07
    	sort
    0.07
    _REC
    0.07
    .namespace
    0.07
    DataSetChanged
    0.07
     norske
    0.07
    違い
    0.06
    _adjust
    0.06
    дж
    0.06
    _DROP
    0.06
    Act Density 0.042%

    No Known Activations