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

    Neuronpedia

    INDEX
    Explanations

    descriptive clothing and product adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ingred
    0.43
     substituents
    0.40
     rulemaking
    0.40
     subordination
    0.38
     enmity
    0.38
     বিরোধিতা
    0.38
    食物
    0.37
     etiology
    0.37
     ingrédients
    0.37
     utterance
    0.37
    POSITIVE LOGITS
     hybrid
    0.48
     lightweight
    0.47
     high
    0.46
     sleeveless
    0.46
     vintage
    0.46
    小型
    0.46
     sleek
    0.45
     compact
    0.44
     specialty
    0.43
     hooded
    0.43
    Act Density 0.147%

    No Known Activations