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

    Neuronpedia

    INDEX
    Explanations

    exclusions from offers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ması
    -0.07
    原谅
    -0.07
    training
    -0.07
    🧔
    -0.07
     tijd
    -0.06
     edad
    -0.06
    Ⴆ
    -0.06
    략
    -0.06
    'autres
    -0.06
     exclusion
    -0.06
    POSITIVE LOGITS
    사무
    0.08
    烏
    0.07
    .DataTable
    0.07
    ｕ
    0.07
    ncia
    0.06
     slideshow
    0.06
     semiclassical
    0.06
    centration
    0.06
    step
    0.06
    athan
    0.06
    Act Density 0.003%

    No Known Activations