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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    澳大
    -0.07
    一大
    -0.07
    	RTLI
    -0.06
    初中
    -0.06
    -provider
    -0.06
    三大
    -0.06
    بالغ
    -0.06
     viruses
    -0.06
    及其他
    -0.06
     الدين
    -0.06
    POSITIVE LOGITS
     Burger
    0.07
    (region
    0.07
    _parm
    0.07
     Display
    0.07
    (worker
    0.07
    ᵌ
    0.07
    между
    0.06
    ");}↵
    0.06
     busc
    0.06
     aquatic
    0.06
    Act Density 0.017%

    No Known Activations