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

    Neuronpedia

    INDEX
    Explanations

    XML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cars
    -0.07
     Kunden
    -0.06
    695
    -0.06
     Nagar
    -0.06
    -floating
    -0.06
    毕
    -0.06
    hof
    -0.06
    592
    -0.06
     foo
    -0.06
     freopen
    -0.06
    POSITIVE LOGITS
     upcoming
    0.07
    .Microsoft
    0.07
     Commentary
    0.07
    ].
    0.07
    _hdr
    0.07
     consenting
    0.06
    بات
    0.06
    ;k
    0.06
     throwable
    0.06
     مشاهده
    0.06
    Act Density 0.000%

    No Known Activations