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

    Neuronpedia

    INDEX
    Explanations

    words starting with Sim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কলাপ
    0.43
     Relating
    0.42
    訒
    0.41
    晰
    0.39
     Countdown
    0.39
    棭
    0.38
     HONOR
    0.37
    elden
    0.37
     Zachary
    0.36
    addena
    0.35
    POSITIVE LOGITS
    Sim
    1.12
     sim
    1.09
    sim
    1.02
    SIM
    0.98
     Sim
    0.93
     SIM
    0.90
     سیم
    0.80
     simul
    0.80
     sims
    0.79
     সিম
    0.78
    Act Density 0.019%

    No Known Activations