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

    Neuronpedia

    INDEX
    Explanations

    question and answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     मन
    -0.07
    separator
    -0.07
    ازم
    -0.07
     Rath
    -0.07
    Registro
    -0.07
     〉
    -0.06
    .exclude
    -0.06
    ópez
    -0.06
    .Ticks
    -0.06
    ultimo
    -0.06
    POSITIVE LOGITS
     Majority
    0.06
    '$
    0.06
    .OrdinalIgnoreCase
    0.05
    Western
    0.05
     deutschland
    0.05
    iku
    0.05
    род
    0.05
    .RegularExpressions
    0.05
     lvl
    0.05
     Ske
    0.05
    Act Density 0.185%

    No Known Activations