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

    Neuronpedia

    INDEX
    Explanations

    export or customization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نفت
    0.37
    ระ
    0.36
     intersections
    0.35
    #%%
    0.34
     riêng
    0.34
     pen
    0.34
    Ohio
    0.34
     puse
    0.34
    氘
    0.34
     ኮ
    0.33
    POSITIVE LOGITS
     বিবিসির
    0.45
     susah
    0.38
     myBuilder
    0.38
     ডাক্ত
    0.38
    amily
    0.37
    ᱶ
    0.37
    LoggedIn
    0.37
    Logged
    0.36
     गौरव
    0.36
     naughty
    0.36
    Act Density 0.094%

    No Known Activations