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

    Neuronpedia

    INDEX
    Explanations

    fighting against or assessment methodologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VEY
    0.47
    细菌
    0.46
    SIAN
    0.46
    වින්
    0.45
     computadora
    0.44
    想想
    0.44
     ер
    0.44
     కొన్ని
    0.44
     словами
    0.44
    Constr
    0.44
    POSITIVE LOGITS
    z
    0.47
    ，
    0.44
    </td>
    0.44
    voting
    0.44
    （
    0.43
    теры
    0.43
    ted
    0.42
     Blockchain
    0.42
    ners
    0.42
     October
    0.41
    Act Density 0.002%

    No Known Activations