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

    Neuronpedia

    INDEX
    Explanations

    programming libraries and modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </
    0.38
    اري
    0.33
    性感
    0.32
    ها
    0.31
    اذ
    0.31
     juez
    0.31
    διά
    0.30
    ឹម
    0.30
    ‌
    0.30
     detain
    0.30
    POSITIVE LOGITS
     वाढत
    0.38
    जव
    0.36
    ounces
    0.35
    ೋದ
    0.35
    <unused38>
    0.35
     হইয়
    0.33
    早就
    0.33
     trabalhar
    0.33
    zeko
    0.33
    놁
    0.32
    Act Density 0.049%

    No Known Activations