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

    Neuronpedia

    INDEX
    Explanations

    written

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prostitutas
    -0.07
    iParam
    -0.07
     Could
    -0.07
     swelling
    -0.07
     capac
    -0.07
    -information
    -0.07
     Princip
    -0.07
    �
    -0.07
     hvad
    -0.06
    إن
    -0.06
    POSITIVE LOGITS
    ISH
    0.07
    کت
    0.06
     Vancouver
    0.06
    ish
    0.06
     facial
    0.06
     hep
    0.06
     кал
    0.06
     auch
    0.06
    `↵
    0.06
    .sql
    0.06
    Act Density 0.001%

    No Known Activations