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

    Neuronpedia

    INDEX
    Explanations

    browser user agents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umls
    0.44
    סי
    0.42
     judg
    0.40
    ッケージ
    0.39
    ون
    0.39
    綰
    0.39
    strtolower
    0.39
    䢀
    0.39
     নং
    0.39
     follicles
    0.38
    POSITIVE LOGITS
    ora
    0.40
    TikTok
    0.39
     Casa
    0.38
     Chrome
    0.38
    ami
    0.37
     Dubai
    0.37
     प्रवासी
    0.37
    Xiaomi
    0.37
    Google
    0.37
    he
    0.36
    Act Density 0.009%

    No Known Activations