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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Walt
    -0.30
    annotate
    -0.26
    éĩĮæĸ¯
    -0.24
    andr
    -0.24
    _VOID
    -0.24
    itsu
    -0.24
    .unknown
    -0.24
    åĪİ
    -0.24
    tfoot
    -0.23
    peak
    -0.23
    POSITIVE LOGITS
     Geh
    0.25
    æĶ¾åģĩ
    0.24
    rum
    0.24
    aby
    0.23
    ureau
    0.23
    绳
    0.23
    åħļåĴĮæĶ¿åºľ
    0.23
    éĺĨ
    0.23
    ż
    0.23
    Parcel
    0.23
    Act Density 0.001%

    No Known Activations