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

    Neuronpedia

    INDEX
    Explanations

    fails to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ir
    0.80
    '
    0.71
    {
    0.70
    риал
    0.63
     blasp
    0.61
    (“
    0.61
    ksi
    0.59
     প্রমাণ
    0.59
    AudioAsset
    0.59
     उबाल
    0.59
    POSITIVE LOGITS
    تي
    0.65
    mcs
    0.63
    中
    0.62
    ↵↵
    0.61
    يل
    0.61
    u
    0.61
     consistently
    0.61
    monthly
    0.58
    我
    0.58
     Wichita
    0.57
    Act Density 0.003%

    No Known Activations