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

    Neuronpedia

    INDEX
    Explanations

    electron movements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पढ़ेंगे
    0.47
     σο
    0.40
     subsistence
    0.39
    ப்பையும்
    0.39
    轼
    0.39
     সক্র
    0.38
    叓
    0.38
    当前的
    0.38
     روسیه
    0.36
    CONCLUSIONS
    0.36
    POSITIVE LOGITS
    얄
    0.40
    ண
    0.40
     fren
    0.39
     Col
    0.38
    ond
    0.37
    Find
    0.36
     vlak
    0.36
    ances
    0.36
    Edit
    0.35
     sound
    0.35
    Act Density 0.000%

    No Known Activations