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

    Neuronpedia

    INDEX
    Explanations

    So

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     گر
    -0.09
     ನಾಗ
    -0.08
     民
    -0.08
     garşy
    -0.08
     modeling
    -0.08
     beobachten
    -0.07
    旧
    -0.07
     tõ
    -0.07
     তদন্ত
    -0.07
    民
    -0.07
    POSITIVE LOGITS
     newline
    0.11
     whitespace
    0.10
    Whitespace
    0.10
    -spacing
    0.09
    delivery
    0.09
     spacing
    0.09
     Delivery
    0.09
     prohibits
    0.09
     formatting
    0.08
     uninterrupted
    0.08
    Act Density 0.006%

    No Known Activations