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

    Neuronpedia

    INDEX
    Explanations

    USPS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حافظ
    -0.06
     SUBSTITUTE
    -0.06
     borç
    -0.06
    .byId
    -0.06
     nettsteder
    -0.06
    attribute
    -0.06
     angrily
    -0.06
     pervasive
    -0.06
     rizik
    -0.06
    arios
    -0.05
    POSITIVE LOGITS
    ishment
    0.07
     Λα
    0.06
    Meg
    0.06
    outing
    0.06
    undreds
    0.06
    Violation
    0.06
    663
    0.06
     FAILURE
    0.06
     #$
    0.06
     Use
    0.06
    Act Density 0.000%

    No Known Activations