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

    Neuronpedia

    INDEX
    Explanations

    Y, Yams, Yield, YOLO, Yahoo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ૄ
    0.55
    toISO
    0.54
    ๚
    0.52
     supernat
    0.52
     employé
    0.52
     पंकज
    0.52
    iéndose
    0.52
     मेवाड़
    0.52
    eran
    0.51
     espèces
    0.51
    POSITIVE LOGITS
    '
    0.92
    "
    0.90
    Y
    0.90
     Y
    0.88
     y
    0.70
    AY
    0.66
    %
    0.66
    YT
    0.64
    0
    0.64
     yang
    0.61
    Act Density 0.080%

    No Known Activations