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

    Neuronpedia

    INDEX
    Explanations

    prejud

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    167
    -0.07
    master
    -0.07
    oce
    -0.06
    ​
    -0.06
    ulner
    -0.06
    とき
    -0.06
    multiple
    -0.06
    _Level
    -0.06
     metabolism
    -0.06
     analogous
    -0.05
    POSITIVE LOGITS
     prejudices
    0.07
     İz
    0.07
     realism
    0.06
     Woody
    0.06
     Cleanup
    0.06
    >>&
    0.06
    `),↵
    0.06
     Early
    0.06
     fantasy
    0.06
     HelloWorld
    0.06
    Act Density 0.000%

    No Known Activations