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

    Neuronpedia

    INDEX
    Explanations

    compiler

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RECORD
    -0.10
     Valentine
    -0.09
    ABSPATH
    -0.08
     spontaneously
    -0.08
    澄清
    -0.07
    terraform
    -0.07
     GPLv
    -0.07
     atual
    -0.07
     À
    -0.07
     dataSnapshot
    -0.07
    POSITIVE LOGITS
     compiler
    0.08
    推理
    0.07
    arked
    0.07
    compiler
    0.06
    Related
    0.06
    (pred
    0.06
     PATH
    0.06
    .sorted
    0.06
    替
    0.06
    スピ
    0.06
    Act Density 0.003%

    No Known Activations