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

    Neuronpedia

    INDEX
    Explanations

    potential hazards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ai
    -0.07
    랑
    -0.06
    (['
    -0.06
     Hóa
    -0.06
     zá
    -0.06
    .Clone
    -0.06
     Chúa
    -0.06
     merely
    -0.06
    _REASON
    -0.06
    파
    -0.06
    POSITIVE LOGITS
     registered
    0.08
     Wisconsin
    0.07
     manganese
    0.06
     SAMPLE
    0.06
    ิกายน
    0.06
     posts
    0.06
     exception
    0.06
    ahn
    0.06
    (ListNode
    0.06
    iggins
    0.06
    Act Density 0.048%

    No Known Activations