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

    Neuronpedia

    INDEX
    Explanations

    nationalities or places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🍘
    1.20
    伷
    1.13
    🤽
    1.10
    రు
    1.09
    了一个
    1.06
     maneiras
    1.01
    湿
    1.00
     colorChoice
    0.99
    🈷
    0.98
    🎑
    0.97
    POSITIVE LOGITS
    al
    2.03
    ar
    2.03
    er
    1.89
    es
    1.86
    e
    1.85
    y
    1.80
    el
    1.78
    an
    1.76
    l
    1.69
    a
    1.63
    Act Density 0.082%

    No Known Activations