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

    Neuronpedia

    INDEX
    Explanations

    safe description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лей
    0.39
     ты
    0.39
     threefold
    0.39
     trifle
    0.38
     ойной
    0.37
     تیم
    0.37
     quelcon
    0.37
    σουν
    0.36
     трубо
    0.36
    qrcode
    0.36
    POSITIVE LOGITS
     laaj
    0.48
     U
    0.41
     expanded
    0.41
     widest
    0.38
     wide
    0.38
    erdale
    0.38
     tall
    0.38
     developed
    0.37
    开发
    0.37
    Tall
    0.37
    Act Density 0.000%

    No Known Activations