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

    Neuronpedia

    INDEX
    Explanations

    during or after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    퐶
    0.45
    ᆸ
    0.42
     паліты
    0.40
    éget
    0.40
    వ్
    0.39
    ádz
    0.39
    ኞ
    0.38
     তারাও
    0.38
    𝚙
    0.38
    撳
    0.38
    POSITIVE LOGITS
     durante
    0.60
    .
    0.60
     the
    0.56
     أثناء
    0.50
     podczas
    0.48
     The
    0.47
     durant
    0.47
     akibat
    0.47
    ↵
    0.46
     during
    0.46
    Act Density 0.024%

    No Known Activations