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

    Neuronpedia

    INDEX
    Explanations

    name followed by delimiter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Community
    0.69
    whose
    0.68
     whose
    0.65
    กลับ
    0.63
     Community
    0.60
     COMMUNITY
    0.60
    Volatility
    0.60
    죽
    0.59
    Nor
    0.59
    知名
    0.59
    POSITIVE LOGITS
     main
    0.82
     '__
    0.79
    __":
    0.77
    main
    0.76
    pendown
    0.69
     tester
    0.69
    žne
    0.69
    __':
    0.67
    ="__
    0.67
    vaise
    0.66
    Act Density 0.062%

    No Known Activations