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

    Neuronpedia

    INDEX
    Explanations

    What doth thou require

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    说完
    0.41
    Gener
    0.39
    িনিয়র
    0.38
    joints
    0.37
    を踏
    0.37
    unker
    0.37
    ровать
    0.36
    ச்
    0.36
    none
    0.36
    σταση
    0.36
    POSITIVE LOGITS
     дзяржа
    0.47
     naturally
    0.46
     afin
    0.45
     jego
    0.42
     Naturally
    0.41
     ergonomics
    0.41
     LN
    0.41
     solemn
    0.40
     RMSE
    0.40
     lange
    0.39
    Act Density 0.001%

    No Known Activations