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

    Neuronpedia

    INDEX
    Explanations

    death/injury

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้ท
    -0.07
    不同的
    -0.07
    οκ
    -0.07
     milfs
    -0.06
    date
    -0.06
     Super
    -0.06
    浪
    -0.06
    ze
    -0.06
     tung
    -0.06
    [train
    -0.06
    POSITIVE LOGITS
    (Context
    0.07
     pinpoint
    0.06
    ीय
    0.06
    ISION
    0.06
    _sibling
    0.06
    .SelectedIndexChanged
    0.06
     artisans
    0.06
     sembl
    0.06
    taking
    0.06
    itial
    0.06
    Act Density 0.071%

    No Known Activations