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

    Neuronpedia

    INDEX
    Explanations

    high quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.79
    erreur
    0.73
    every
    0.72
    affichage
    0.72
    appareil
    0.71
    ك
    0.70
    vase
    0.68
    analyze
    0.68
    ować
    0.68
    ент
    0.67
    POSITIVE LOGITS
     Sci
    0.67
     Kis
    0.66
     Mack
    0.64
     Wis
    0.63
     hikers
    0.63
     stands
    0.62
     worded
    0.62
    дра
    0.61
     rivets
    0.61
     revenues
    0.61
    Act Density 0.000%

    No Known Activations