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

    Neuronpedia

    INDEX
    Explanations

    color representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gauss
    -0.07
     foil
    -0.07
     colored
    -0.07
     Odin
    -0.06
    eti
    -0.06
     convenient
    -0.06
     폴
    -0.06
     HL
    -0.06
     rect
    -0.06
     Jessie
    -0.06
    POSITIVE LOGITS
     مست
    0.06
     investing
    0.06
    _TEST
    0.06
     méd
    0.06
     stad
    0.06
    595
    0.06
     Syracuse
    0.06
    remaining
    0.06
     ट
    0.06
    797
    0.06
    Act Density 0.023%

    No Known Activations