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

    Neuronpedia

    INDEX
    Explanations

    diet, Metabolism, Blood Sugar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SECRET
    0.51
     secre
    0.51
     insulin
    0.49
     секре
    0.47
     SECRET
    0.47
     eryth
    0.47
     secreted
    0.46
     secretory
    0.46
     erit
    0.46
     инсу
    0.46
    POSITIVE LOGITS
     Niko
    0.41
    不安定
    0.38
    楼主
    0.37
    தாய
    0.36
    বিজ
    0.35
    αλ
    0.34
     kait
    0.34
     Hox
    0.34
     possess
    0.33
     Al
    0.33
    Act Density 0.020%

    No Known Activations