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

    Neuronpedia

    INDEX
    Explanations

    main activity or form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Woodland
    0.43
     Objetivo
    0.42
     imag
    0.41
     Sess
    0.40
     hào
    0.40
    untary
    0.39
     Lite
    0.39
     imagin
    0.39
     Beth
    0.38
    फिक
    0.38
    POSITIVE LOGITS
    MainBinding
    0.82
    主
    0.61
     main
    0.59
    main
    0.59
    Main
    0.54
     mainline
    0.53
     Main
    0.52
     MainActivity
    0.51
    MainActivity
    0.50
    MAIN
    0.48
    Act Density 0.000%

    No Known Activations