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

    Neuronpedia

    INDEX
    Explanations

    often used, potentially allowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ב
    0.51
    活躍
    0.45
     intervalles
    0.44
    ２
    0.44
    獧
    0.43
    NA
    0.41
     unterschiedlich
    0.41
    2
    0.41
     Mint
    0.41
     перечис
    0.41
    POSITIVE LOGITS
    ധിപ
    0.43
    诲
    0.41
    räger
    0.41
    ρίας
    0.40
     তারই
    0.40
     இப்பட
    0.40
    toByteArray
    0.39
     Прави
    0.39
    ’
    0.39
     addressing
    0.39
    Act Density 0.004%

    No Known Activations