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

    Neuronpedia

    INDEX
    Explanations

    architectural glass, installation, acceptance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     graduellement
    0.47
    Historically
    0.47
    रिक
    0.46
    Uber
    0.46
    Primitive
    0.45
     المصفوفه
    0.45
     Veamos
    0.44
     किन्तु
    0.44
    BatchNorm
    0.43
    Deaths
    0.43
    POSITIVE LOGITS
    ≙
    0.83
     TÜ
    0.74
     WLAN
    0.73
     (=
    0.70
     Mitarbeiter
    0.66
     „
    0.65
     Gä
    0.64
     individuell
    0.64
     besonders
    0.61
     digitalisation
    0.61
    Act Density 0.044%

    No Known Activations