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

    Neuronpedia

    INDEX
    Explanations

    website links and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ƾ
    1.07
    uillez
    1.04
    काच्या
    1.04
    getStringExtra
    1.01
    鳇
    1.00
    ेडियम
    0.99
    <unused928>
    0.99
     Thành
    0.99
    ruktur
    0.99
    主角
    0.98
    POSITIVE LOGITS
    eigen
    0.92
     kok
    0.85
     lat
    0.79
    Purpose
    0.78
     WHY
    0.77
    তঃ
    0.77
    purpose
    0.77
    ے
    0.76
     eigen
    0.76
     sende
    0.75
    Act Density 0.002%

    No Known Activations