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

    Neuronpedia

    INDEX
    Explanations

    code snippets or structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wymien
    0.38
    郓
    0.36
    ृता
    0.36
     организм
    0.34
    рых
    0.34
    何を
    0.34
    ТИ
    0.34
     alimentaires
    0.33
    Bed
    0.33
    葡萄
    0.33
    POSITIVE LOGITS
     또는
    0.59
     using
    0.56
    或其他
    0.55
     only
    0.54
     hoặc
    0.54
     then
    0.53
     αλλά
    0.52
     或
    0.52
     অথবা
    0.52
     And
    0.52
    Act Density 0.161%

    No Known Activations