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

    Neuronpedia

    INDEX
    Explanations

    timeout, request, sleep, management, behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     име
    1.06
     scient
    0.93
     senior
    0.92
     annual
    0.89
     Sustain
    0.89
     جنوبی
    0.89
    l
    0.87
    yzed
    0.87
    ijer
    0.83
    وست
    0.82
    POSITIVE LOGITS
     Caesar
    1.25
    czas
    1.15
    determining
    1.15
    tting
    1.12
     सेंटीमीटर
    1.11
     drooping
    1.10
    く
    1.09
     setTimeout
    1.08
    ◃
    1.08
    taire
    1.08
    Act Density 0.001%

    No Known Activations