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

    Neuronpedia

    INDEX
    Explanations

    n-word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initWithStyle
    -0.06
    getMock
    -0.06
    (chart
    -0.06
    xcb
    -0.06
     Cait
    -0.06
     healer
    -0.06
     在线
    -0.06
    pcl
    -0.06
    幸福
    -0.06
    [Math
    -0.06
    POSITIVE LOGITS
     Negro
    0.07
     registros
    0.07
     transforms
    0.07
     negro
    0.07
     Register
    0.07
    arr
    0.07
    Register
    0.07
     inferior
    0.07
     ас
    0.06
    igger
    0.06
    Act Density 0.005%

    No Known Activations