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

    Neuronpedia

    INDEX
    Explanations

    colon and parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mutil
    -0.07
    ](↵
    -0.07
     Sauce
    -0.07
     jó
    -0.06
    Amb
    -0.06
    \Helper
    -0.06
    )",
↵
    -0.06
     chill
    -0.06
     hust
    -0.06
    ratio
    -0.06
    POSITIVE LOGITS
     Poland
    0.07
     Wy
    0.07
    reece
    0.07
    реди
    0.06
    Scientists
    0.06
    prak
    0.06
    ुर
    0.06
    ashire
    0.06
     Asus
    0.06
    -Origin
    0.06
    Act Density 0.006%

    No Known Activations