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

    Neuronpedia

    INDEX
    Explanations

    URLs and informative content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sini
    0.71
     configured
    0.65
    껑
    0.64
     truy
    0.62
     કરતા
    0.62
     möglich
    0.59
     journey
    0.59
     take
    0.59
     lament
    0.58
     möglichen
    0.58
    POSITIVE LOGITS
    ",[(
    0.78
    ומ
    0.77
    roductive
    0.73
    न्होंने
    0.73
    ടും
    0.72
    ਾਕ
    0.68
    >[</
    0.66
    spirator
    0.66
    MTAB
    0.65
    Faces
    0.65
    Act Density 0.004%

    No Known Activations