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

    Neuronpedia

    INDEX
    Explanations

    moving into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ์
    0.40
    }
    0.39
    ("
    0.36
    res
    0.36
    ers
    0.35
     alkene
    0.35
    諄
    0.35
    ်
    0.34
    არის
    0.34
     erzählen
    0.34
    POSITIVE LOGITS
     других
    0.49
     ON
    0.45
    xD
    0.44
     другие
    0.43
     시간을
    0.42
     similar
    0.41
     Nordstrom
    0.41
     Shopify
    0.41
     rhythm
    0.40
     descuento
    0.40
    Act Density 0.007%

    No Known Activations