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

    Neuronpedia

    INDEX
    Explanations

    code and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ونکو
    0.41
    usi
    0.39
     अन
    0.37
    ைகள்
    0.37
     yür
    0.36
     ব্রাহ্মণ
    0.36
    Shang
    0.36
     φω
    0.36
     bags
    0.35
    bag
    0.35
    POSITIVE LOGITS
     Subscription
    0.41
    Subscription
    0.39
     subscription
    0.37
    FileReader
    0.37
    版权
    0.37
     feeling
    0.37
    *)&
    0.37
    odium
    0.36
    クラブ
    0.36
    醎
    0.36
    Act Density 0.000%

    No Known Activations