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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jsx
    -0.06
     DESCRIPTION
    -0.06
     düş
    -0.06
    整
    -0.06
    ír
    -0.06
     Луч
    -0.06
    ským
    -0.06
     chết
    -0.06
    uo
    -0.06
     deployment
    -0.06
    POSITIVE LOGITS
     підт
    0.07
     startY
    0.07
     تد
    0.06
    ically
    0.06
     допом
    0.06
    ісля
    0.06
    pgsql
    0.06
    олод
    0.06
    fullname
    0.06
    ertain
    0.06
    Act Density 0.251%

    No Known Activations