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

    Neuronpedia

    INDEX
    Explanations

    Asset pipeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pn
    0.43
    frak
    0.39
    nth
    0.39
     blissful
    0.39
    ஸ்வர
    0.38
    left
    0.38
    hit
    0.37
    nP
    0.37
    /*.
    0.37
    ಬಿ
    0.37
    POSITIVE LOGITS
    ારીખ
    0.39
     আদেশ
    0.37
     Non
    0.37
    চ্ছে
    0.36
     antonio
    0.36
     ресурсов
    0.36
     órdenes
    0.36
     decompose
    0.35
     non
    0.35
     tradeoff
    0.35
    Act Density 0.000%

    No Known Activations