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

    Neuronpedia

    INDEX
    Explanations

    std::fs operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্ড
    0.50
    的时
    0.45
     starboard
    0.44
     점에서
    0.43
    neux
    0.42
    getInfo
    0.42
    畊
    0.42
     brewed
    0.42
    urgia
    0.41
     kraju
    0.41
    POSITIVE LOGITS
     Gson
    0.54
    берите
    0.50
    ेन
    0.48
     millioner
    0.46
    𝑚
    0.45
    zicht
    0.44
    д
    0.44
     permitt
    0.44
     ধাক
    0.44
    ти
    0.44
    Act Density 0.004%

    No Known Activations