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

    Neuronpedia

    INDEX
    Explanations

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unpopular
    -0.06
     absolutely
    -0.06
     retain
    -0.06
    制造
    -0.06
     cooks
    -0.06
    _LOOKUP
    -0.06
     обст
    -0.06
    الق
    -0.06
    中的
    -0.06
    =@"
    -0.05
    POSITIVE LOGITS
    _wifi
    0.07
    annis
    0.07
    idae
    0.06
     Cent
    0.06
     sincerely
    0.06
    rowse
    0.06
     موفق
    0.06
     fibers
    0.06
     gar
    0.06
    .Book
    0.06
    Act Density 0.005%

    No Known Activations