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

    Neuronpedia

    INDEX
    Explanations

    URLs and search queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ambul
    0.66
    ENU
    0.64
     ars
    0.64
     Нача
    0.63
     воро
    0.63
    我自己
    0.63
     നേരി
    0.62
     EDC
    0.61
    encie
    0.61
     અમારા
    0.61
    POSITIVE LOGITS
     QString
    0.84
    type
    0.79
     -"
    0.78
    인
    0.78
     explained
    0.76
    site
    0.76
    Eq
    0.75
     explain
    0.74
     type
    0.73
    懷
    0.73
    Act Density 0.140%

    No Known Activations