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

    Neuronpedia

    INDEX
    Explanations

    punctuation and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.44
    ↵↵↵
    0.39
    ↵
    0.35
    ↵↵↵↵↵
    0.34
            
    0.33
    ↵↵↵↵
    0.32
    .'
    0.31
     .'
    0.30
    小說
    0.30
       
    0.30
    POSITIVE LOGITS
    σιμοποι
    0.37
    вый
    0.35
    लेषण
    0.35
    と思いますが
    0.34
     будь
    0.33
     thậm
    0.33
    ENDMENT
    0.32
     previewBuilder
    0.32
     mMediaPlayer
    0.32
     lesz
    0.32
    Act Density 0.000%

    No Known Activations