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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comed
    -0.08
    accom
    -0.08
     assignments
    -0.07
     że
    -0.07
     Geschichte
    -0.07
     pills
    -0.07
     sims
    -0.07
     ghetto
    -0.07
     Broadcasting
    -0.07
    apol
    -0.07
    POSITIVE LOGITS
    átní
    0.06
    larımız
    0.06
     gratuite
    0.06
     vmax
    0.06
     aVar
    0.06
     الصن
    0.05
    .NewLine
    0.05
    حب
    0.05
     newData
    0.05
    0.05
    Act Density 0.007%

    No Known Activations