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

    Neuronpedia

    INDEX
    Explanations

    coordination or routing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ｲ
    0.47
    殮
    0.47
    宩
    0.44
    โทษ
    0.44
    𒅀
    0.44
    로운
    0.44
    ANDEZ
    0.44
    swürdig
    0.43
    )^\
    0.42
    ه
    0.42
    POSITIVE LOGITS
     alongside
    0.47
     to
    0.44
     capables
    0.44
     online
    0.43
     in
    0.43
     bridges
    0.42
     exclusively
    0.41
     Lakes
    0.41
     jest
    0.41
    打算
    0.41
    Act Density 0.002%

    No Known Activations