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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ife
    -0.07
    _fence
    -0.07
    :[[
    -0.07
     handsome
    -0.07
    gerät
    -0.06
     ():
    -0.06
    뷘
    -0.06
    _cb
    -0.06
    .progress
    -0.06
    ufe
    -0.06
    POSITIVE LOGITS
    มน
    0.07
    少了
    0.07
     cloning
    0.07
    �
    0.07
     separate
    0.07
     Australian
    0.07
    另一个
    0.06
    means
    0.06
     ion
    0.06
     appending
    0.06
    Act Density 0.002%

    No Known Activations