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

    Neuronpedia

    INDEX
    Explanations

    multi-lingual punctuation and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kick
    0.57
    дору
    0.55
     Sedona
    0.54
    Daisy
    0.51
     checklist
    0.51
     Orlando
    0.51
     Kick
    0.51
    PG
    0.50
     Georgian
    0.50
    Gaia
    0.49
    POSITIVE LOGITS
    ಲ್
    0.59
     calcule
    0.56
    assem
    0.56
    ointment
    0.55
     recombination
    0.54
     третий
    0.54
     dolore
    0.53
    のデザイン
    0.52
     विक्रय
    0.51
    。\
    0.51
    Act Density 0.000%

    No Known Activations