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

    Neuronpedia

    INDEX
    Explanations

    closures and classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sly
    -0.09
    .Positive
    -0.08
    Positive
    -0.07
     positive
    -0.07
     refin
    -0.07
     positiva
    -0.07
    positive
    -0.07
     yard
    -0.07
     alter
    -0.07
    _positive
    -0.07
    POSITIVE LOGITS
     Rural
    0.09
     verticale
    0.09
    (vertical
    0.08
     Plaint
    0.08
     vertical
    0.08
    vertical
    0.08
     freeze
    0.08
     المناطق
    0.08
     formazione
    0.08
     sâu
    0.08
    Act Density 0.001%

    No Known Activations