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

    Neuronpedia

    INDEX
    Explanations

    assembly instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विजे
    0.41
    ்க
    0.39
    学校
    0.37
    いきます
    0.37
     وبالتالي
    0.37
    ั
    0.37
    するため
    0.36
    িক্ষ
    0.36
    SVM
    0.35
    無視
    0.35
    POSITIVE LOGITS
     spleen
    0.43
     stomach
    0.43
     incest
    0.43
     wretched
    0.40
     notori
    0.40
     evanes
    0.39
     Phang
    0.39
     cellulite
    0.39
     Stam
    0.38
     saucer
    0.38
    Act Density 0.000%

    No Known Activations