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

    Neuronpedia

    INDEX
    Explanations

    legal offenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    08
    -0.07
    hosts
    -0.06
     mai
    -0.06
    _decode
    -0.06
     밤
    -0.06
     pans
    -0.06
    ذر
    -0.06
    ign
    -0.06
    fecha
    -0.06
    env
    -0.06
    POSITIVE LOGITS
    .ResponseWriter
    0.07
    ...↵↵↵↵
    0.06
     Evangel
    0.06
     exposition
    0.06
     adorn
    0.06
    sizeof
    0.06
     meteor
    0.06
    xoops
    0.06
     Gee
    0.06
     shuts
    0.06
    Act Density 0.021%

    No Known Activations