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

    Neuronpedia

    INDEX
    Explanations

    open source and transparency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रत्ये
    0.54
    व्यक्तित्व
    0.47
     दुर्भाग्य
    0.43
    創造
    0.42
    鎗
    0.42
     inevitable
    0.40
     व्यक्तित्व
    0.39
    不幸
    0.39
    倉
    0.39
    ത്തിലൂടെ
    0.39
    POSITIVE LOGITS
    不用
    0.44
    不怕
    0.42
     does
    0.41
     redness
    0.40
     თავ
    0.39
    sees
    0.38
     bekommt
    0.38
     არა
    0.38
     doesn
    0.37
     Gets
    0.37
    Act Density 0.004%

    No Known Activations