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

    Neuronpedia

    INDEX
    Explanations

    lists and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ร
    0.45
     되
    0.45
    ownic
    0.44
     βρί
    0.43
     potrz
    0.43
    주고
    0.42
    误
    0.42
     vuonna
    0.41
    ва
    0.40
    В
    0.40
    POSITIVE LOGITS
     estimates
    0.48
     retailers
    0.48
     regimens
    0.46
     finalists
    0.45
    ABILITY
    0.45
    یمپ
    0.44
     allergens
    0.44
     күн
    0.44
    க்கணக்கான
    0.43
    candidates
    0.42
    Act Density 0.003%

    No Known Activations