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

    Neuronpedia

    INDEX
    Explanations

    adding complexity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nový
    -0.08
     конеч
    -0.08
     zukünft
    -0.08
    ু
    -0.08
    UMMY
    -0.08
     règ
    -0.07
     toekomstige
    -0.07
     setiap
    -0.07
     rapides
    -0.07
    -0.07
    POSITIVE LOGITS
     deeper
    0.10
     sophistication
    0.10
    advanced
    0.10
     Advanced
    0.10
     progressively
    0.10
     diversification
    0.10
     gradually
    0.09
     progressivement
    0.09
     bigger
    0.09
    Advanced
    0.09
    Act Density 0.072%
    No Known Activations