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

    Neuronpedia

    INDEX
    Explanations

    foundation for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     principles
    0.45
    Mapper
    0.40
    श्‍
    0.39
     Charlie
    0.39
     महत्व
    0.38
     Principles
    0.38
     pocos
    0.38
     सर्दी
    0.37
     некоторые
    0.36
    Prin
    0.36
    POSITIVE LOGITS
    財務
    0.42
     நிறுத்த
    0.42
     fundament
    0.42
    herlands
    0.42
    žit
    0.42
    🥱
    0.41
    थुरा
    0.41
    suptitle
    0.40
    uchsia
    0.40
    OCUS
    0.39
    Act Density 0.001%

    No Known Activations