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

    Neuronpedia

    INDEX
    Explanations

    at once

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     हेतु
    0.39
     GAO
    0.38
    aturing
    0.38
    eringen
    0.38
     anomal
    0.37
    terminus
    0.37
    ründ
    0.37
     herbicide
    0.36
    pler
    0.36
     selectable
    0.36
    POSITIVE LOGITS
     Crochet
    0.40
     gym
    0.40
    盯着
    0.40
    WithPath
    0.39
    同時
    0.39
     expo
    0.39
    MatContext
    0.38
    到时候
    0.38
     airport
    0.38
    有时候
    0.38
    Act Density 0.009%

    No Known Activations