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

    Neuronpedia

    INDEX
    Explanations

    questions starting with do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.91
    й
    0.79
     কেমন
    0.79
    ি
    0.79
    Jahr
    0.77
    いま
    0.76
    Calories
    0.75
    ي
    0.75
    做什么
    0.74
    Motivation
    0.73
    POSITIVE LOGITS
     tubercle
    0.83
     you
    0.79
     there
    0.77
     strtoupper
    0.74
     every
    0.73
     [
    0.70
     There
    0.69
     roadside
    0.68
     codebase
    0.68
     surgeons
    0.68
    Act Density 0.086%

    No Known Activations