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

    Neuronpedia

    INDEX
    Explanations

    C++ code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hol
    -0.07
     filmed
    -0.07
    ɲ
    -0.07
    ﾐ
    -0.07
    包子
    -0.07
    传
    -0.07
    潇
    -0.06
     buf
    -0.06
    ✈
    -0.06
     Wed
    -0.06
    POSITIVE LOGITS
     potentials
    0.08
     Problems
    0.08
    会让你
    0.07
     realities
    0.07
    Kernel
    0.07
     halls
    0.07
     Rates
    0.07
    _strategy
    0.07
     girls
    0.07
     Slots
    0.07
    Act Density 0.009%

    No Known Activations