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

    Neuronpedia

    INDEX
    Explanations

    war, keyword recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     findAll
    0.44
     automated
    0.41
    automated
    0.41
     automaty
    0.40
     vatandaş
    0.39
     listOf
    0.39
     automating
    0.39
     mongoose
    0.39
     Automated
    0.39
    automate
    0.38
    POSITIVE LOGITS
    兵
    0.40
     Crescent
    0.37
     soldiers
    0.37
    椇
    0.36
     soldados
    0.36
    ner
    0.35
     توصیه
    0.35
     folded
    0.35
    vě
    0.34
    ppled
    0.34
    Act Density 0.000%

    No Known Activations