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

    Neuronpedia

    INDEX
    Explanations

    storage requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     done
    0.46
     Done
    0.46
     nav
    0.45
    usk
    0.43
    enn
    0.43
     goes
    0.43
    Nav
    0.43
     kullanılır
    0.42
    ่ง
    0.42
     is
    0.42
    POSITIVE LOGITS
    🔯
    0.54
    0.53
     trauer
    0.49
    ເລັກ
    0.48
    0.48
    CLUD
    0.47
    含む
    0.47
     priests
    0.47
    }}^
    0.47
    䥑
    0.46
    Act Density 0.004%

    No Known Activations