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

    Neuronpedia

    INDEX
    Explanations

    online resources and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    COMANDA
    0.46
    𒁀
    0.42
    OLYBD
    0.42
     আসন
    0.42
    AMINATION
    0.41
    duced
    0.41
     Tomlin
    0.41
    修士
    0.41
    盱
    0.41
    èdes
    0.41
    POSITIVE LOGITS
     …
    0.43
     ….
    0.41
     https
    0.40
     Free
    0.39
     i
    0.37
    i
    0.36
    ↵
    0.36
     An
    0.36
      
    0.33
     g
    0.32
    Act Density 0.061%

    No Known Activations