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

    Neuronpedia

    INDEX
    Explanations

    code and concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulasi
    0.66
     สอบ
    0.65
    ilih
    0.61
    лыгы
    0.58
    olu
    0.57
    कन्या
    0.57
    ursa
    0.57
    edu
    0.56
    agma
    0.56
    expo
    0.56
    POSITIVE LOGITS
    大きい
    0.68
     gigantic
    0.64
     AMAZING
    0.64
     大きい
    0.62
     largeur
    0.62
     bastante
    0.61
     richtige
    0.60
     GREAT
    0.58
     كبير
    0.57
     COLLISIONS
    0.57
    Act Density 0.000%

    No Known Activations