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

    Neuronpedia

    INDEX
    Explanations

    ful

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ত
    -0.07
     dragons
    -0.07
    d
    -0.06
     phone
    -0.06
     sdk
    -0.06
    🍫
    -0.06
    etat
    -0.06
    🌿
    -0.06
    谁知道
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     العملية
    0.07
    Middle
    0.07
    儒家
    0.07
    יג
    0.07
    omin
    0.06
    _definitions
    0.06
     *>
    0.06
     фильм
    0.06
    illes
    0.06
     المسلمين
    0.06
    Act Density 0.054%

    No Known Activations