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

    Neuronpedia

    INDEX
    Explanations

    roughly equivalent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    続く
    0.86
    дцать
    0.82
    𝑝
    0.79
    тья
    0.79
     принимать
    0.75
     выше
    0.75
     обы
    0.72
     операций
    0.72
     выбирать
    0.71
    いう
    0.70
    POSITIVE LOGITS
     ceram
    0.91
     menus
    0.82
     furs
    0.80
     murs
    0.80
     immobili
    0.77
     gonf
    0.75
     lím
    0.73
     anc
    0.72
     hearth
    0.72
     dand
    0.72
    Act Density 0.000%

    No Known Activations