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

    Neuronpedia

    INDEX
    Explanations

    Code and technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     libero
    -0.08
     uncon
    -0.07
     banned
    -0.07
     colorful
    -0.07
     têm
    -0.07
    多彩
    -0.07
    יפה
    -0.07
     الإيراني
    -0.07
     tofu
    -0.07
     polít
    -0.07
    POSITIVE LOGITS
    .ab
    0.08
    くなる
    0.08
    ";
    0.07
    /';↵
    0.07
     Essentials
    0.07
    .closest
    0.07
    _LCD
    0.07
    ILITIES
    0.07
     Wilson
    0.07
    ,True
    0.07
    Act Density 0.000%

    No Known Activations