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

    Neuronpedia

    INDEX
    Explanations

    OU

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fourier
    -0.07
    constraint
    -0.06
    ustering
    -0.06
     ")↵
    -0.05
     "\">
    -0.05
    接着
    -0.05
    space
    -0.05
     endoth
    -0.05
     λ
    -0.05
     Pow
    -0.05
    POSITIVE LOGITS
    BundleOrNil
    0.07
     música
    0.07
     adulti
    0.06
     now
    0.06
     loud
    0.06
     crave
    0.06
     Bakanı
    0.06
     dut
    0.06
    aled
    0.06
    _hor
    0.06
    Act Density 0.003%

    No Known Activations