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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doses
    -0.08
    COORD
    -0.07
    ğın
    -0.07
     Budget
    -0.07
    ضو
    -0.07
    れ
    -0.06
    Budget
    -0.06
    zo
    -0.06
    -largest
    -0.06
    Fashion
    -0.06
    POSITIVE LOGITS
     Mime
    0.07
     прот
    0.07
    \grid
    0.07
    lobber
    0.06
     sku
    0.06
     змі
    0.06
     rej
    0.06
     Μον
    0.06
    >';
    0.06
    >';
↵
    0.06
    Act Density 0.037%

    No Known Activations