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

    Neuronpedia

    INDEX
    Explanations

    our / ours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ral
    0.39
    Huge
    0.38
    Fuel
    0.37
    рят
    0.37
    /
    0.37
    Rose
    0.36
    0.36
    }(\
    0.35
     fuel
    0.35
     rounded
    0.34
    POSITIVE LOGITS
     нашего
    0.50
     our
    0.47
     nossos
    0.46
     meiosis
    0.45
     unseres
    0.45
     нынеш
    0.43
     nosso
    0.43
     naš
    0.43
     unserer
    0.42
     должна
    0.41
    Act Density 0.000%

    No Known Activations