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

    Neuronpedia

    INDEX
    Explanations

    fermion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     آباد
    -0.07
     López
    -0.07
    лей
    -0.07
    ismo
    -0.06
    ”—
    -0.06
     endurance
    -0.06
     cực
    -0.06
     Mate
    -0.06
     Horse
    -0.06
     liver
    -0.06
    POSITIVE LOGITS
    (off
    0.07
     порядке
    0.06
    _ASM
    0.06
     apprentices
    0.06
    	using
    0.06
    iggers
    0.06
     knowledgeable
    0.06
    쇼
    0.06
    台灣
    0.06
    法院
    0.06
    Act Density 0.003%

    No Known Activations