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

    Neuronpedia

    INDEX
    Explanations

    instead of relying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਾਂ
    0.52
    iteten
    0.51
    broccoli
    0.45
    ྥ
    0.44
    耑
    0.44
    astype
    0.43
    sets
    0.42
    িয়া
    0.42
    SCHOOL
    0.42
    ariyati
    0.42
    POSITIVE LOGITS
     denote
    0.47
     doc
    0.46
     keep
    0.45
     resurrected
    0.43
     scrutin
    0.42
     render
    0.42
     date
    0.41
     leave
    0.41
     say
    0.41
     permanent
    0.41
    Act Density 0.004%

    No Known Activations