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

    Neuronpedia

    INDEX
    Explanations

    deciding priority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     St
    0.45
     trans
    0.42
     Ál
    0.42
     피
    0.41
    ör
    0.41
    specific
    0.41
     in
    0.40
     be
    0.40
     Quer
    0.40
    Sear
    0.40
    POSITIVE LOGITS
     prioritization
    1.75
     priorities
    1.66
     приорите
    1.66
     priorit
    1.62
     prioritized
    1.62
     priority
    1.59
     prioritize
    1.59
     prioritizing
    1.59
    优先级
    1.57
    優先
    1.56
    Act Density 0.090%

    No Known Activations