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

    Neuronpedia

    INDEX
    Explanations

    punctuation: colon and period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FormField
    -0.07
    альних
    -0.07
    _WARNING
    -0.07
    ENT
    -0.07
    quine
    -0.07
     лет
    -0.06
    ром
    -0.06
     Cuisine
    -0.06
     Pond
    -0.06
     stockings
    -0.06
    POSITIVE LOGITS
    MethodManager
    0.06
     enam
    0.06
     balık
    0.06
    MT
    0.06
     tongues
    0.06
     fireworks
    0.06
    ukarı
    0.06
     рез
    0.05
    赛
    0.05
    .EntityFramework
    0.05
    Act Density 0.081%

    No Known Activations