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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deletes
    -0.07
     Knife
    -0.06
     pul
    -0.06
    Drag
    -0.06
     hed
    -0.06
    (resultSet
    -0.06
    :])
    -0.06
     Hed
    -0.06
     Boat
    -0.06
     crude
    -0.06
    POSITIVE LOGITS
    ,'']]],↵
    0.07
    меж
    0.06
    duplicate
    0.06
    something
    0.06
    NESS
    0.06
    twenty
    0.06
     pong
    0.06
    �
    0.06
     specificity
    0.06
     ngồi
    0.06
    Act Density 0.014%

    No Known Activations