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

    Neuronpedia

    INDEX
    Explanations

    health organizations and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.99
    v
    0.99
    es
    0.96
    م
    0.96
    一
    0.87
     khỏe
    0.86
    糖尿病
    0.84
    ే
    0.84
     होता
    0.84
     ఆరోగ
    0.82
    POSITIVE LOGITS
     it
    1.25
     the
    1.06
    ۰
    1.01
    :
    0.97
     '
    0.91
     reorgan
    0.91
     length
    0.90
     comedy
    0.89
     trigonometric
    0.88
    liği
    0.88
    Act Density 0.006%

    No Known Activations