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

    Neuronpedia

    INDEX
    Explanations

    legal requirements and income

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     하지만
    1.02
     unapolog
    1.00
     illetve
    0.95
     ಉಪಯೋಗ
    0.91
     foundational
    0.90
     uptick
    0.86
     veía
    0.86
    aunque
    0.85
     añade
    0.83
     livestream
    0.82
    POSITIVE LOGITS
     conditionally
    1.18
     №
    1.03
     ​​
    1.01
     XNUMX
    0.98
     с
    0.96
     и
    0.95
     incompre
    0.94
     analogues
    0.92
     ​​​​
    0.92
     к
    0.91
    Act Density 0.006%

    No Known Activations