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

    Neuronpedia

    INDEX
    Explanations

    award

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Main
    -0.08
    _AV
    -0.07
     execute
    -0.07
    SendMessage
    -0.07
    ListView
    -0.07
     europe
    -0.07
    Unity
    -0.07
    空
    -0.06
    (ns
    -0.06
    ं
    -0.06
    POSITIVE LOGITS
     Educational
    0.07
     Wahl
    0.07
    洗礼
    0.07
    ammers
    0.07
    .attack
    0.07
    רצי
    0.07
    🦑
    0.07
    กระท
    0.06
     disqualified
    0.06
    拗
    0.06
    Act Density 0.018%

    No Known Activations