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

    Neuronpedia

    INDEX
    Explanations

    code licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _unref
    -0.07
    ONGODB
    -0.07
    쓰
    -0.07
     yabanc
    -0.07
     masculine
    -0.07
     yabancı
    -0.07
    ocurrency
    -0.06
     Recipe
    -0.06
    EEE
    -0.06
    ㉡
    -0.06
    POSITIVE LOGITS
    ál
    0.08
    arser
    0.07
    趙
    0.07
    (steps
    0.07
    uttle
    0.07
    🐡
    0.07
    될
    0.07
    赵
    0.07
     cannons
    0.07
    يبة
    0.06
    Act Density 0.001%

    No Known Activations