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

    Neuronpedia

    INDEX
    Explanations

    Methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cloud
    -0.06
     detection
    -0.06
    sol
    -0.06
     whit
    -0.06
     getToken
    -0.06
     gray
    -0.06
     Dix
    -0.06
     passes
    -0.06
    结构
    -0.06
     witty
    -0.06
    POSITIVE LOGITS
     залиш
    0.07
    cmpeq
    0.06
     ■
    0.06
    ernote
    0.06
     [
    0.06
     gấp
    0.06
     RectTransform
    0.06
    istrov
    0.06
     opting
    0.06
    .*,
    0.06
    Act Density 0.001%

    No Known Activations