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

    Neuronpedia

    INDEX
    Explanations

    real estate, real izes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     espe
    2.09
    1.98
    1.88
     atrav
    1.88
     Penelope
    1.86
     dizer
    1.83
    Ⓘ
    1.83
    عيه
    1.82
    زالة
    1.79
    _'.$
    1.79
    POSITIVE LOGITS
    <bos>
    1.69
    burst
    1.53
    습니다
    1.47
    push
    1.45
    stylish
    1.44
    st
    1.41
    다
    1.41
    cstring
    1.39
    pox
    1.39
    collider
    1.38
    Act Density 0.000%

    No Known Activations