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
    蓝
    -0.07
    _datasets
    -0.07
     KD
    -0.07
     Maxim
    -0.07
    pcl
    -0.07
     Luigi
    -0.06
    hook
    -0.06
    _ENT
    -0.06
     lọc
    -0.06
    actors
    -0.06
    POSITIVE LOGITS
     дух
    0.06
     advertis
    0.06
    .Mon
    0.06
    ěj
    0.06
    <quote
    0.06
     Crowley
    0.06
     Torah
    0.06
     Noir
    0.06
    　�
    0.06
     práv
    0.06
    Act Density 0.009%

    No Known Activations