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

    Neuronpedia

    INDEX
    Explanations

    and, comma, period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >{"
    -0.07
    زن
    -0.06
    ("")]↵
    -0.06
     Security
    -0.06
     Notification
    -0.06
     Marine
    -0.06
    ΜΑ
    -0.06
    .zero
    -0.06
    izr
    -0.06
    pheric
    -0.06
    POSITIVE LOGITS
     monot
    0.07
    freq
    0.07
     fodder
    0.07
        
    0.06
    grey
    0.06
    [array
    0.06
     je
    0.06
     […]...↵
    0.06
     jars
    0.06
    0.06
    Act Density 0.067%

    No Known Activations