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

    Neuronpedia

    INDEX
    Explanations

    want to help you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chỉ
    0.64
    唾
    0.59
    筠
    0.59
     값이
    0.57
    പ്പോൾ
    0.57
     인터넷
    0.56
    鸦
    0.56
     الإنترنت
    0.55
    ოდ
    0.54
    NSIndexPath
    0.54
    POSITIVE LOGITS
    your
    0.73
    urro
    0.70
    你的
    0.66
     потребности
    0.66
    uet
    0.65
    any
    0.63
     your
    0.62
    早速
    0.61
    Your
    0.61
    nombre
    0.61
    Act Density 0.028%

    No Known Activations