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

    Neuronpedia

    INDEX
    Explanations

    behavioral analysis planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chickens
    0.52
     repetition
    0.43
    鶏
    0.42
     viande
    0.42
    Meat
    0.41
     fishes
    0.40
     repetitions
    0.40
     Coch
    0.40
    meat
    0.39
     meat
    0.39
    POSITIVE LOGITS
     analysis
    0.50
     ABA
    0.48
     Analysis
    0.47
    dataFormat
    0.46
     analyzed
    0.45
    Analysis
    0.44
     injector
    0.44
     analý
    0.44
     анализ
    0.43
     анали
    0.42
    Act Density 0.010%

    No Known Activations