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

    Neuronpedia

    INDEX
    Explanations

    iterator in programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我们
    -0.84
     Româ
    -0.84
     dedicato
    -0.84
    get
    -0.79
    一定
    -0.78
    是
    -0.78
     estrema
    -0.78
    的
    -0.77
    就是
    -0.76
    所以
    -0.76
    POSITIVE LOGITS
     it
    1.26
    怂
    1.01
     estí
    0.95
     injust
    0.93
     sabias
    0.91
    דיה
    0.91
     itr
    0.91
     reposer
    0.90
     EACH
    0.90
    を発見
    0.89
    Act Density 0.008%

    No Known Activations