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

    Neuronpedia

    INDEX
    Explanations

    viewport meta tag initial-scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     থাকিলেও
    0.43
    stringValue
    0.38
    ោយ
    0.38
     drowned
    0.38
     methylation
    0.36
    ರವ
    0.36
     grise
    0.36
    Shakespeare
    0.36
     newborns
    0.36
     olefins
    0.35
    POSITIVE LOGITS
     shrink
    0.99
    shrink
    0.91
    Shr
    0.86
     Shr
    0.85
     shrinks
    0.85
     shrinking
    0.83
     shrank
    0.80
     shrunk
    0.79
     shrinkage
    0.79
    縮
    0.73
    Act Density 0.005%

    No Known Activations