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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ui
    -0.07
     selecion
    -0.06
     hans
    -0.06
     Quit
    -0.06
     kans
    -0.06
     enc
    -0.06
     менее
    -0.06
    子は
    -0.06
    UID
    -0.06
     dét
    -0.06
    POSITIVE LOGITS
     Madagascar
    0.07
    family
    0.06
     Amerika
    0.06
     reconnect
    0.06
     را
    0.06
    客
    0.06
     Bij
    0.06
     Halloween
    0.06
    />\
    0.06
    060
    0.06
    Act Density 0.002%

    No Known Activations