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

    Neuronpedia

    INDEX
    Explanations

    main and section tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2052>
    0.40
    ReLU
    0.39
    yspace
    0.38
    Michigan
    0.38
    titleTextStyle
    0.38
    इयों
    0.37
    RuL
    0.37
    Ḥ
    0.37
    Extreme
    0.36
    äten
    0.36
    POSITIVE LOGITS
     id
    0.57
     arial
    0.42
    id
    0.39
     aria
    0.39
     Georg
    0.37
    >
    0.37
     actions
    0.36
     pioneers
    0.36
     equally
    0.36
    行为
    0.36
    Act Density 0.004%

    No Known Activations