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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (condition
    -0.07
    chl
    -0.07
     Rockies
    -0.07
     sposób
    -0.07
     Healthcare
    -0.07
    岛
    -0.07
    asdf
    -0.06
    (rd
    -0.06
     JSImport
    -0.06
    ixe
    -0.06
    POSITIVE LOGITS
     func
    0.07
    normal
    0.06
    rně
    0.06
    "type
    0.06
     sorted
    0.06
     FUNC
    0.06
     digestive
    0.06
    coffee
    0.06
     SCH
    0.06
    rine
    0.06
    Act Density 0.003%

    No Known Activations