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

    Neuronpedia

    INDEX
    Explanations

    just…

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eer
    1.07
    ez
    0.91
    ek
    0.86
    eers
    0.81
    eur
    0.78
    ۰۰
    0.77
    ﺰ
    0.77
     kanamycin
    0.76
    ม
    0.76
    я
    0.75
    POSITIVE LOGITS
    PAss
    0.72
    र
    0.72
    er
    0.71
     mey
    0.70
    ievements
    0.67
     penetrating
    0.66
    frm
    0.66
    OURCES
    0.66
    erade
    0.65
    ایش
    0.65
    Act Density 0.013%

    No Known Activations