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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ara
    -0.07
    /q
    -0.07
     ARR
    -0.07
     ACE
    -0.07
    aktu
    -0.07
     Qi
    -0.07
     ما
    -0.07
     athletes
    -0.07
     arcs
    -0.07
     tw
    -0.07
    POSITIVE LOGITS
     milfs
    0.07
    nestjs
    0.06
     فرودگاه
    0.06
    冠
    0.06
    nofollow
    0.06
     mundane
    0.06
    .OrderByDescending
    0.06
    eygamber
    0.05
    -haspopup
    0.05
    rtle
    0.05
    Act Density 0.045%

    No Known Activations