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

    Neuronpedia

    INDEX
    Explanations

    moons of Jupiter and Saturn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.56
    aghan
    0.52
    on
    0.50
    o
    0.49
     pernyataan
    0.48
     rupam
    0.47
     chords
    0.47
     अंक
    0.47
     wills
    0.47
    ø
    0.46
    POSITIVE LOGITS
     Фа
    0.52
     RAF
    0.52
    Фа
    0.52
     LNG
    0.51
     razem
    0.51
    独自の
    0.51
     Sas
    0.51
     registrado
    0.50
     Livraison
    0.50
    Ра
    0.50
    Act Density 0.012%

    No Known Activations