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

    Neuronpedia

    INDEX
    Explanations

    src/ directory in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    东西
    0.44
     Rosen
    0.40
    JY
    0.39
    Rosen
    0.38
     Gulf
    0.38
     Sequence
    0.37
    bacher
    0.37
     Sequences
    0.37
     Downey
    0.37
     Seventh
    0.36
    POSITIVE LOGITS
     main
    0.43
    Madam
    0.43
    main
    0.41
    و
    0.40
     내
    0.39
    جام
    0.39
    મુ
    0.38
     madam
    0.38
     uite
    0.38
     상관
    0.37
    Act Density 0.002%

    No Known Activations