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

    Neuronpedia

    INDEX
    Explanations

    bolded words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    allaitement
    0.50
    쐞
    0.47
     thalassemia
    0.46
    ಹಾಸ
    0.46
     ചെറിയ
    0.45
    ཎ
    0.44
    0.44
    oclonal
    0.44
    ーストラリア
    0.43
    ToReference
    0.42
    POSITIVE LOGITS
    /
    0.48
     for
    0.47
     d
    0.46
     brilliance
    0.45
     good
    0.44
     Salt
    0.43
     great
    0.42
     worthwhile
    0.42
     Q
    0.41
     More
    0.41
    Act Density 0.004%

    No Known Activations