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

    Neuronpedia

    INDEX
    Explanations

    customer identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Unlock
    0.44
    䄸
    0.44
    業
    0.43
    โรง
    0.41
     வர
    0.40
    浪
    0.40
    elcome
    0.38
    aula
    0.38
    Lines
    0.38
    imbangan
    0.37
    POSITIVE LOGITS
    矇
    0.40
    आरटी
    0.38
    ຕິດຕ
    0.38
     bereit
    0.37
     oint
    0.36
    ദു
    0.36
    HttpGet
    0.36
     heady
    0.36
    ೀಲ
    0.35
    TargetFramework
    0.35
    Act Density 0.001%

    No Known Activations