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

    Neuronpedia

    INDEX
    Explanations

    um

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inicial
    -0.06
     Diane
    -0.06
     ragazzo
    -0.06
    �
    -0.06
     *((
    -0.06
     Victoria
    -0.06
     &[
    -0.06
     Giles
    -0.06
     Cli
    -0.06
     JText
    -0.06
    POSITIVE LOGITS
    baum
    0.27
     Baum
    0.22
    UM
    0.13
    um
    0.11
     Raum
    0.10
    ums
    0.08
     plummet
    0.08
    ,num
    0.08
    rum
    0.08
    au
    0.07
    Act Density 0.002%

    No Known Activations