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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "$
    -0.07
    lined
    -0.07
    芒
    -0.07
    平均水平
    -0.07
     ='
    -0.07
     보기
    -0.07
    endir
    -0.07
    none
    -0.07
    getConnection
    -0.07
    意境
    -0.07
    POSITIVE LOGITS
     misma
    0.08
    	game
    0.08
    に対
    0.08
     filho
    0.07
     prosecution
    0.07
     idol
    0.07
     الدفاع
    0.07
    Mother
    0.07
    	ct
    0.07
    igkeit
    0.07
    Act Density 0.001%

    No Known Activations