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

    Neuronpedia

    INDEX
    Explanations

    numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuore
    0.67
     obtenus
    0.65
     majority
    0.64
     disarmament
    0.63
     fillet
    0.61
     continued
    0.60
     remain
    0.60
     subtype
    0.60
    มากมาย
    0.60
     lack
    0.59
    POSITIVE LOGITS
    2
    1.33
     ۲۰
    1.24
    ۲۰
    1.17
    २०
    1.04
     २०२२
    1.01
    1
    1.00
    ತೆ
    0.95
    ٢
    0.95
    ২০
    0.93
    १९
    0.92
    Act Density 0.069%

    No Known Activations