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

    Neuronpedia

    INDEX
    Explanations

    sentence starters and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     readiness
    0.43
    ruce
    0.41
     grim
    0.39
     labored
    0.39
     sorg
    0.38
    quiry
    0.38
    حال
    0.38
     TPR
    0.38
    敢
    0.37
     It
    0.37
    POSITIVE LOGITS
     epitope
    0.58
    Property
    0.57
    وی
    0.55
    요
    0.54
    پا
    0.52
     операция
    0.52
     менедж
    0.52
    គាត់
    0.52
    হে
    0.52
    жена
    0.51
    Act Density 0.001%

    No Known Activations