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

    Neuronpedia

    INDEX
    Explanations

    identifying problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yetiştir
    -0.07
     preferredStyle
    -0.06
     діяль
    -0.06
     discs
    -0.06
     活
    -0.06
    のだ
    -0.06
    wner
    -0.06
     twilight
    -0.06
    OpenHelper
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Arrange
    0.07
    ná
    0.07
    าสตร
    0.06
    Fade
    0.06
     comput
    0.06
     Progress
    0.06
    Psi
    0.06
    �
    0.06
     SDK
    0.06
     arm
    0.06
    Act Density 0.003%

    No Known Activations