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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ethiopia
    -0.07
    ís
    -0.07
    โทษ
    -0.07
    iership
    -0.07
    افة
    -0.06
    ﺄ
    -0.06
     Серг
    -0.06
    .write
    -0.06
    mother
    -0.06
    رد
    -0.06
    POSITIVE LOGITS
    🗣
    0.08
     sucking
    0.08
     grounded
    0.07
     titanium
    0.07
     salle
    0.07
    (txt
    0.07
     paradigm
    0.07
     kiên
    0.07
     flatten
    0.07
    得到有效
    0.07
    Act Density 0.018%

    No Known Activations