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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    버
    -0.08
     author
    -0.07
    ittel
    -0.06
    력을
    -0.06
     Commands
    -0.06
    .frequency
    -0.06
    .offer
    -0.06
    .groups
    -0.06
    PixelFormat
    -0.06
     solved
    -0.06
    POSITIVE LOGITS
     정말
    0.06
    Working
    0.06
     Working
    0.06
     abide
    0.06
     efekt
    0.06
    agents
    0.06
    počet
    0.06
    MF
    0.06
     paddingRight
    0.06
    deal
    0.06
    Act Density 0.003%

    No Known Activations