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

    Neuronpedia

    INDEX
    Explanations

    invisible marker or lighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dane
    0.66
     reach
    0.65
     Desar
    0.64
     intelectual
    0.62
     anger
    0.62
     acuerdos
    0.60
    atoria
    0.60
     roug
    0.59
     autor
    0.58
     real
    0.57
    POSITIVE LOGITS
     Aś
    1.09
     tidak
    1.08
     staining
    1.05
    ྵ
    1.04
    Returning
    1.04
    㔯
    1.03
    𐰆
    1.02
     Tint
    1.02
    寶寶
    1.01
     jsem
    1.01
    Act Density 0.000%

    No Known Activations