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

    Neuronpedia

    INDEX
    Explanations

    here's how and let me know if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    私たちは
    0.27
     enormes
    0.27
    BUT
    0.27
     soooo
    0.26
     usamos
    0.24
     addirittura
    0.24
    真正
    0.23
    আমরা
    0.23
     जुनून
    0.23
     সত্যিকার
    0.23
    POSITIVE LOGITS
     GPT
    0.26
    ↵↵
    0.26
     revised
    0.25
     markdown
    0.25
     the
    0.24
    GPT
    0.24
      
    0.24
     improved
    0.24
     ChatGPT
    0.24
    y
    0.24
    Act Density 0.155%

    No Known Activations