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

    Neuronpedia

    INDEX
    Explanations

    old history stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    protobuf
    0.47
    tencent
    0.46
     Residences
    0.41
     তি
    0.38
     erasing
    0.38
     cts
    0.38
     incessantly
    0.38
    छत्तीस
    0.37
    ctu
    0.36
    🎍
    0.36
    POSITIVE LOGITS
     múlt
    0.41
     cross
    0.41
    History
    0.40
     Geschichte
    0.40
    ි
    0.38
    降
    0.38
     Thickness
    0.38
     मानदंडों
    0.38
    Thickness
    0.37
     Time
    0.37
    Act Density 0.001%

    No Known Activations