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

    Neuronpedia

    INDEX
    Explanations

    using `xhost +local:`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ClNO
    0.52
     ప్రక
    0.49
    డీపీ
    0.46
    ക്കാര
    0.45
    జేపీ
    0.45
    这也
    0.44
     ২০২৩
    0.44
     också
    0.43
    蒈
    0.43
    <unused74>
    0.43
    POSITIVE LOGITS
    ↵
    0.51
     dure
    0.48
    ements
    0.46
    uli
    0.45
     langue
    0.45
    ilians
    0.45
    ummers
    0.45
     I
    0.45
    늘
    0.44
    agger
    0.44
    Act Density 0.004%

    No Known Activations