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

    Neuronpedia

    INDEX
    Explanations

    prob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PROGRAM
    -0.07
    _URI
    -0.07
     wow
    -0.07
    gulp
    -0.07
    getEmail
    -0.07
    ernote
    -0.06
    -map
    -0.06
    ANGO
    -0.06
     Rape
    -0.06
     hmm
    -0.06
    POSITIVE LOGITS
     ellos
    0.08
    约为
    0.08
    볼
    0.07
    ﭵ
    0.07
    icias
    0.07
     Difficulty
    0.07
    ías
    0.06
    lux
    0.06
    鲑
    0.06
    }];↵
    0.06
    Act Density 0.001%

    No Known Activations