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

    Neuronpedia

    INDEX
    Explanations

    legitimate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     graduate
    0.54
     mentor
    0.53
     generative
    0.52
    graduate
    0.50
     dow
    0.49
     leader
    0.47
     ghost
    0.46
     gate
    0.46
     neural
    0.46
     powered
    0.46
    POSITIVE LOGITS
    үн
    0.50
    Quantidade
    0.49
     importants
    0.48
    پاکستان
    0.47
    انیہ
    0.47
    ্তার
    0.47
    ²',
    0.46
    ವಿದೆ
    0.46
    ాత్రి
    0.46
    肨
    0.45
    Act Density 0.008%

    No Known Activations