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

    Neuronpedia

    INDEX
    Explanations

    describing lists and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    শাক
    0.42
    ኀ
    0.41
     ಮನೆ
    0.40
    蓼
    0.39
     তদ
    0.38
     strips
    0.37
    ozygous
    0.37
    顯
    0.37
     மனை
    0.37
    ሥ
    0.37
    POSITIVE LOGITS
     появится
    0.46
     noting
    0.45
     появля
    0.42
     появ
    0.41
    pointing
    0.40
     incluindo
    0.40
     glances
    0.40
     highlighting
    0.39
     خصوص
    0.39
     balanced
    0.39
    Act Density 0.005%

    No Known Activations