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

    Neuronpedia

    INDEX
    Explanations

    explaining why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eigens
    0.45
    push
    0.43
    抬
    0.41
     University
    0.41
     What
    0.40
     Necessary
    0.39
     Drive
    0.38
     Need
    0.38
    Push
    0.38
     uwagę
    0.38
    POSITIVE LOGITS
     else
    0.52
    soever
    0.50
    ELSE
    0.48
     it
    0.46
    rop
    0.45
     प्रत्येक
    0.44
     itd
    0.44
    aturated
    0.43
    টু
    0.43
    нэ
    0.43
    Act Density 0.010%

    No Known Activations