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

    Neuronpedia

    INDEX
    Explanations

    bioadhesive, GPT-4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     possa
    0.52
     você
    0.50
     jeopardize
    0.47
     jogador
    0.46
     suffice
    0.46
     acquaint
    0.45
     you
    0.44
     souhaite
    0.43
     nella
    0.43
    जोरी
    0.43
    POSITIVE LOGITS
     ಸಾಮ
    0.45
     বিজ্ঞানীরা
    0.42
     благодаря
    0.40
     теле
    0.40
    虽
    0.38
    銀
    0.38
    Thousands
    0.38
    雖
    0.38
     gồm
    0.37
     Органи
    0.37
    Act Density 0.027%

    No Known Activations