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

    Neuronpedia

    INDEX
    Explanations

    times and states

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    리지
    0.40
    不
    0.37
    ại
    0.37
     όχι
    0.37
    待
    0.36
     çıktı
    0.36
     मेरे
    0.36
     my
    0.35
     voltam
    0.35
    bdb
    0.35
    POSITIVE LOGITS
    Thr
    0.40
    opt
    0.39
     absolutely
    0.39
    افه
    0.39
    Sem
    0.38
     LAP
    0.38
    absolutely
    0.38
     comput
    0.37
    elie
    0.37
    LAP
    0.37
    Act Density 0.000%

    No Known Activations