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

    Neuronpedia

    INDEX
    Explanations

    tuples in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oster
    0.29
    Ни
    0.29
     thank
    0.28
    qua
    0.28
    yming
    0.28
    感谢
    0.28
    rą
    0.28
    响起
    0.28
    Western
    0.27
    iamy
    0.27
    POSITIVE LOGITS
     مص
    0.30
     vortex
    0.29
     הראשון
    0.29
     Poz
    0.28
     Chancellor
    0.28
     আত্মসম
    0.28
     Tal
    0.27
     assassination
    0.27
    0.27
     sealant
    0.27
    Act Density 0.008%

    No Known Activations