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

    Neuronpedia

    INDEX
    Explanations

    introduces explanations of lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ິນ
    0.84
    ంటి
    0.83
     bebés
    0.82
     beberapa
    0.82
     explanations
    0.80
     деталей
    0.80
    बैंड
    0.79
     설명을
    0.79
     eines
    0.79
    CLUDES
    0.76
    POSITIVE LOGITS
    not
    0.79
    𝗔
    0.73
    ,"
    0.70
    ত্যাশিত
    0.70
    ，”
    0.68
    ʜ
    0.67
     important
    0.67
    crum
    0.66
     not
    0.66
     ome
    0.65
    Act Density 0.138%

    No Known Activations