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

    Neuronpedia

    INDEX
    Explanations

    file paths and metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jakarta
    0.38
     JUnit
    0.38
     বিকাল
    0.38
    junit
    0.37
     Wald
    0.37
    sounds
    0.37
    osts
    0.37
    crystals
    0.37
    }}<
    0.36
    estas
    0.36
    POSITIVE LOGITS
    FilePath
    0.47
     funzione
    0.43
     aquele
    0.43
    ）：
    0.43
     功能
    0.42
     做
    0.41
    ⇀
    0.41
    功能
    0.41
    אה
    0.41
     funkce
    0.41
    Act Density 0.003%

    No Known Activations