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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recreate
    -0.06
     "@"
    -0.06
    /location
    -0.06
    ...↵↵↵
    -0.06
     Austral
    -0.06
     mirror
    -0.06
     niece
    -0.06
    orange
    -0.06
     *"
    -0.06
     favourite
    -0.06
    POSITIVE LOGITS
    vrir
    0.07
    ác
    0.07
    .[
    0.06
    .toolStripSeparator
    0.06
    Outcome
    0.06
     Nä
    0.06
    Bill
    0.06
     jylland
    0.06
    ā
    0.06
    disk
    0.06
    Act Density 0.158%

    No Known Activations