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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Matrix
    -0.07
    aleur
    -0.07
     　　　　　　　　　　
    -0.07
     COLUMN
    -0.07
    　 　
    -0.07
    _matrix
    -0.07
    (direction
    -0.06
    _previous
    -0.06
    　　　　　　　　　　
    -0.06
     Accountability
    -0.06
    POSITIVE LOGITS
    -fed
    0.06
    ivet
    0.06
    荣
    0.06
     меди
    0.06
    ูด
    0.06
     psychosis
    0.06
    	old
    0.06
     약
    0.06
     bên
    0.06
    �
    0.06
    Act Density 0.005%

    No Known Activations