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

    Neuronpedia

    INDEX
    Explanations

    Food

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xda
    -0.07
    秕
    -0.07
    툩
    -0.07
     الخل
    -0.06
    马来
    -0.06
    垾
    -0.06
     white
    -0.06
     Sweep
    -0.06
     shade
    -0.06
    link
    -0.06
    POSITIVE LOGITS
                                ↵
    0.07
    感觉自己
    0.07
    摇
    0.07
    0.07
    ᐡ
    0.07
    ❚
    0.07
    nosti
    0.07
    arkin
    0.07
    姨
    0.07
     sometime
    0.07
    Act Density 0.020%

    No Known Activations