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

    Neuronpedia

    INDEX
    Explanations

    "and" followed by pronouns or articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    スの
    0.48
     იყოს
    0.46
    渶
    0.45
    特的
    0.44
    ouilles
    0.44
    小于
    0.43
    ری
    0.43
    твы
    0.42
    ্রের
    0.42
    炵
    0.41
    POSITIVE LOGITS
    1
    0.63
    2
    0.55
    0.55
     !)
    0.53
    9
    0.52
    0
    0.52
    .
    0.50
    şağı
    0.49
    :}
    0.49
    қа
    0.48
    Act Density 0.038%

    No Known Activations