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

    Neuronpedia

    INDEX
    Explanations

    decoding, riddles, and language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     renewables
    0.55
     négoci
    0.54
     consultative
    0.51
     kebijakan
    0.50
     decisões
    0.50
     აღმასრულ
    0.49
     webinars
    0.48
     dépenses
    0.48
     eSIM
    0.48
    iduciary
    0.47
    POSITIVE LOGITS
     vowels
    0.88
     spelling
    0.83
     anagram
    0.82
    anagram
    0.79
     vowel
    0.78
     misspelled
    0.78
     phonetic
    0.75
    Anagram
    0.75
     words
    0.73
    字母
    0.73
    Act Density 0.306%

    No Known Activations