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

    Neuronpedia

    INDEX
    Explanations

    ZH followed by Q

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chacune
    1.98
     memastikan
    1.63
     liens
    1.54
     nós
    1.52
     ouvr
    1.52
     coval
    1.52
     foster
    1.50
     pes
    1.45
    ς
    1.45
    ঞ্চল্য
    1.44
    POSITIVE LOGITS
    من
    1.82
     surrounded
    1.80
    یز
    1.70
     семь
    1.64
     Surrounded
    1.62
     laundry
    1.53
    ا
    1.47
     ماہ
    1.46
     Generally
    1.46
    GameObject
    1.44
    Act Density 0.000%

    No Known Activations