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

    Neuronpedia

    INDEX
    Explanations

    sofas and couches

    np_acts-logits-general · gemini-2.5-flash-lite

    furnishings and wearable comfort items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    锄
    0.56
    flowers
    0.55
     a
    0.55
    ఓ
    0.55
    ล
    0.52
    "
    0.51
    Flowers
    0.50
    支付宝
    0.50
    Р
    0.50
    Z
    0.49
    POSITIVE LOGITS
     ベッド
    0.71
    ir
    0.70
    🛌
    0.64
     mattress
    0.61
     パンツ
    0.59
    ię
    0.57
     sofa
    0.55
     cómodo
    0.54
    床上
    0.54
     cómoda
    0.53
    Act Density 0.266%

    No Known Activations