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

    Neuronpedia

    INDEX
    Explanations

    'H' or 'h'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鈈
    0.76
    詓
    0.73
    Mâc
    0.70
    ⴳ
    0.69
     afterDir
    0.67
    ຽງ
    0.65
     ராஜ
    0.65
    Ὀ
    0.65
    ゚
    0.64
    ្វី
    0.62
    POSITIVE LOGITS
    H
    2.03
     H
    2.02
     ハ
    1.95
    ハ
    1.92
     h
    1.84
     ஹ
    1.82
     ഹ
    1.80
     HT
    1.79
     HC
    1.76
    Ｈ
    1.75
    Act Density 0.927%

    No Known Activations