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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itemBuilder
    -0.56
     stolz
    -0.51
     }}"></
    -0.49
    Jedis
    -0.47
    din
    -0.45
    d
    -0.45
    escudo
    -0.43
     Sixth
    -0.43
     Like
    -0.43
    unsqueeze
    -0.43
    POSITIVE LOGITS
     if
    0.77
    ArrowToggle
    0.70
    ValueStyle
    0.66
    bootstrapcdn
    0.66
     kasarigan
    0.65
    下载附件
    0.60
     expressed
    0.59
    msgSender
    0.58
     advertised
    0.56
    发表于
    0.55
    Act Density 0.001%

    No Known Activations