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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    园
    -0.07
     Lincoln
    -0.07
     случаев
    -0.07
     आश
    -0.06
     Trevor
    -0.06
    _dynamic
    -0.06
     çıkış
    -0.06
     central
    -0.06
     Sto
    -0.06
     franca
    -0.06
    POSITIVE LOGITS
     spy
    0.07
     Urs
    0.07
     gain
    0.06
     berg
    0.06
    prend
    0.06
    .dep
    0.06
    pedia
    0.06
    (rx
    0.06
    شهر
    0.06
    ichick
    0.06
    Act Density 0.006%

    No Known Activations