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

    Neuronpedia

    INDEX
    Explanations

    will recognize, the ancestor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mox
    0.48
     Bagan
    0.48
     chis
    0.48
     Moya
    0.48
     Gottlieb
    0.48
    KeyboardView
    0.47
    ímp
    0.47
     imbib
    0.46
     embal
    0.46
     indul
    0.46
    POSITIVE LOGITS
     >
    0.47
    ++
    0.45
    {
    0.44
    وري
    0.42
    <0x80>
    0.41
    шу
    0.41
    _
    0.41
    >
    0.41
    女朋友
    0.40
    ﺟ
    0.39
    Act Density 0.006%

    No Known Activations