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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ig
    -0.07
     nexus
    -0.07
     fh
    -0.07
     or
    -0.07
     festen
    -0.07
    .msg
    -0.06
     sản
    -0.06
    -0.06
     nating
    -0.06
     miglior
    -0.06
    POSITIVE LOGITS
    izielle
    0.10
     സ്ഥിരീകര
    0.09
     Banque
    0.09
    (actual
    0.09
     matches
    0.09
     מעל
    0.08
     kët
    0.08
     confirms
    0.08
     منه
    0.08
     เดือน
    0.08
    Act Density 0.015%
    No Known Activations