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

    Neuronpedia

    INDEX
    Explanations

    schools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ming
    -0.06
    >`;↵
    -0.06
     fearless
    -0.06
     swing
    -0.06
    .isfile
    -0.06
     Null
    -0.06
    udies
    -0.06
    aris
    -0.06
     Gender
    -0.06
    身体
    -0.06
    POSITIVE LOGITS
    <strong
    0.07
     Pay
    0.07
    Drv
    0.07
    ً،
    0.07
    Act
    0.07
    ---</
    0.06
    Shoot
    0.06
    Exporter
    0.06
    Cow
    0.06
    ogenerated
    0.06
    Act Density 0.000%

    No Known Activations