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

    Neuronpedia

    INDEX
    Explanations

    superlative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сложные
    0.47
     اسمه
    0.45
     временем
    0.43
     smrti
    0.43
    форм
    0.41
     რა
    0.41
     treści
    0.40
    épaisseur
    0.40
    ństw
    0.40
     имена
    0.40
    POSITIVE LOGITS
     largest
    0.55
     smallest
    0.47
    Largest
    0.47
     longest
    0.46
     slowest
    0.46
     highest
    0.45
    largest
    0.44
     fastest
    0.44
     Largest
    0.44
     widest
    0.43
    Act Density 0.021%

    No Known Activations