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

    Neuronpedia

    INDEX
    Explanations

    fruits and vegetables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ED
    0.55
    ರ್
    0.52
    SES
    0.51
     jedna
    0.50
    မှာ
    0.50
    م
    0.49
    ient
    0.48
    upiter
    0.48
    SUB
    0.48
    :
    0.48
    POSITIVE LOGITS
     vegetables
    0.57
    野菜
    0.55
     Vegetables
    0.54
     unbreakable
    0.54
    𝑜
    0.52
    鲐
    0.49
     veggies
    0.49
    蕉
    0.49
    🍊
    0.48
     Calibri
    0.48
    Act Density 0.003%

    No Known Activations