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

    Neuronpedia

    INDEX
    Explanations

    file extension naming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Relatively
    0.87
    PNG
    0.81
     VMs
    0.77
     Tanz
    0.77
     Patrim
    0.76
    வர்களுக்கு
    0.76
    Công
    0.76
    第二个
    0.73
    ொருள்
    0.71
     Công
    0.71
    POSITIVE LOGITS
     master
    0.81
    olist
    0.78
     geworden
    0.77
     मास्टर
    0.76
     entitled
    0.76
     untitled
    0.72
    master
    0.72
    йд
    0.72
    概要
    0.72
     MASTER
    0.71
    Act Density 0.106%

    No Known Activations