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

    Neuronpedia

    INDEX
    Explanations

    Associated Press

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이
    1.16
    ے
    1.06
    emphasis
    1.03
    гле
    1.02
     albeit
    1.00
     hearted
    0.99
    甾
    0.99
     golden
    0.98
     anden
    0.98
     allegation
    0.98
    POSITIVE LOGITS
     riscos
    1.35
     transferência
    1.31
    ciation
    1.27
     redor
    1.26
     cierta
    1.24
     peligros
    1.24
    amese
    1.24
     стала
    1.23
    ্ধ্য
    1.22
     tecnica
    1.21
    Act Density 0.023%

    No Known Activations