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

    Neuronpedia

    INDEX
    Explanations

    Yields and yogurt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पंकज
    0.55
    rophages
    0.54
    inį
    0.54
    nements
    0.54
    inę
    0.53
    ૄ
    0.53
    an
    0.52
     இரா
    0.52
    ర్జ
    0.52
     புத்தக
    0.51
    POSITIVE LOGITS
    '
    0.90
    "
    0.87
     Y
    0.86
    Y
    0.81
     y
    0.72
     yang
    0.61
    0
    0.61
    %
    0.59
    YT
    0.58
     YG
    0.57
    Act Density 0.280%

    No Known Activations