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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    María
    0.45
    माष्टमी
    0.45
    SRPI
    0.44
     habeas
    0.44
     एसएसपी
    0.44
     levando
    0.43
    嶌
    0.43
     चौटाला
    0.43
    uggling
    0.42
    ExpressCheckout
    0.42
    POSITIVE LOGITS
     adjectives
    0.82
     adjective
    0.76
     word
    0.63
     qualities
    0.59
     characteristics
    0.52
     attributes
    0.48
     synonyms
    0.47
     descriptions
    0.47
     anton
    0.47
     glitter
    0.46
    Act Density 0.083%

    No Known Activations