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

    Neuronpedia

    INDEX
    Explanations

    Military

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    छ
    -0.07
     وه
    -0.07
    čně
    -0.07
    racak
    -0.07
     renal
    -0.07
    munition
    -0.07
    elen
    -0.07
     CX
    -0.06
    gere
    -0.06
     welt
    -0.06
    POSITIVE LOGITS
    算
    0.06
    -loving
    0.06
    子
    0.06
    医院
    0.06
    Enc
    0.06
    =true
    0.06
    лав
    0.06
    善
    0.06
     약
    0.06
    inner
    0.06
    Act Density 0.003%

    No Known Activations