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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Za
    -0.07
    erea
    -0.07
    Organ
    -0.06
    相信
    -0.06
    ebin
    -0.06
     цього
    -0.06
    No
    -0.06
    Death
    -0.06
     lời
    -0.06
    ivid
    -0.06
    POSITIVE LOGITS
     preprocessing
    0.08
     OF
    0.06
    _INTER
    0.06
    入口
    0.06
    .criteria
    0.06
     searchText
    0.06
     constituent
    0.06
     percentages
    0.06
    相当
    0.06
    .ReadToEnd
    0.06
    Act Density 0.010%

    No Known Activations