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

    Neuronpedia

    INDEX
    Explanations

    military titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Swedish
    -0.07
    -lock
    -0.06
    amm
    -0.06
     gift
    -0.06
     Kelley
    -0.06
     executives
    -0.06
    Selective
    -0.06
    oodoo
    -0.06
     причины
    -0.06
     الحر
    -0.06
    POSITIVE LOGITS
     :.
    0.08
    .AI
    0.07
     Harry
    0.07
     Colonel
    0.06
    /**↵
    0.06
     Uncomment
    0.06
    **,
    0.06
    ù
    0.06
    gt
    0.06
    ｢
    0.06
    Act Density 0.014%

    No Known Activations