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

    Neuronpedia

    INDEX
    Explanations

    text alignment center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +{\
    0.46
    &=&
    0.44
     top
    0.44
     топ
    0.43
    Compressed
    0.42
    道府県
    0.42
     dokt
    0.41
    覦
    0.41
     cannula
    0.40
     courbes
    0.40
    POSITIVE LOGITS
     align
    0.85
     textAlign
    0.79
     TextAlign
    0.75
    align
    0.74
    TextAlign
    0.70
    textAlign
    0.67
     alignment
    0.65
    center
    0.63
     Align
    0.63
    alignment
    0.61
    Act Density 0.009%

    No Known Activations