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

    Neuronpedia

    INDEX
    Explanations

    medal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .LINE
    -0.07
    —who
    -0.07
     guardian
    -0.06
     storyboard
    -0.06
    �
    -0.06
    [var
    -0.06
     Intersection
    -0.06
     awakening
    -0.06
    bour
    -0.06
     Parenthood
    -0.06
    POSITIVE LOGITS
     Medal
    0.15
     medal
    0.12
     medals
    0.09
    DSL
    0.07
    рал
    0.07
     Token
    0.07
     Shelf
    0.07
    edo
    0.07
    UNDLE
    0.06
     Del
    0.06
    Act Density 0.002%

    No Known Activations