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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stripe
    -0.07
     beet
    -0.07
    Dirs
    -0.06
    امة
    -0.06
     incontri
    -0.06
     уз
    -0.06
    Page
    -0.06
    Wenn
    -0.06
     snaží
    -0.06
    周收录
    -0.06
    POSITIVE LOGITS
     hire
    0.07
    ANCELED
    0.07
     ủy
    0.07
     anarchists
    0.06
    ////////////////////////////////////////////////////////////////////////////
    0.06
     they
    0.06
     kişisel
    0.06
    pixels
    0.06
     PV
    0.06
     достат
    0.06
    Act Density 0.022%

    No Known Activations