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

    Neuronpedia

    INDEX
    Explanations

    Provides explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fors
    -0.08
    Hey
    -0.08
     Hey
    -0.08
    _AI
    -0.08
    fors
    -0.07
     Ik
    -0.07
     totaling
    -0.07
     Thing
    -0.07
     ਦਾ
    -0.07
     Bh
    -0.07
    POSITIVE LOGITS
     ermöglicht
    0.11
     permettant
    0.10
     позволяет
    0.10
     позволяют
    0.09
     permitindo
    0.09
     enables
    0.09
     ermöglichen
    0.09
     позволя
    0.09
     allowing
    0.09
     açısından
    0.09
    Act Density 0.293%

    No Known Activations