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

    Neuronpedia

    INDEX
    Explanations

    drawing, produced, purely, direct, missiles, village, meeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Islands
    0.52
    قاف
    0.49
    uhe
    0.45
     bulkhead
    0.45
    拁
    0.43
    が行
    0.43
    رحبا
    0.43
    䓶
    0.43
     रिली
    0.43
     SUVs
    0.43
    POSITIVE LOGITS
    4
    0.60
    6
    0.55
    נ
    0.54
    resolution
    0.53
    5
    0.50
    Depois
    0.50
    3
    0.49
    ll
    0.49
    Chrome
    0.49
    sketch
    0.48
    Act Density 0.000%

    No Known Activations