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

    Neuronpedia

    INDEX
    Explanations

    S

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蚯
    0.32
    :\
    0.31
    '\
    0.29
     kasutada
    0.29
    
    0.29
     gratuita
    0.29
    />
    0.29
    ]
    0.29
    $.
    0.28
    обходимо
    0.28
    POSITIVE LOGITS
    কে
    0.35
    рида
    0.34
    ćem
    0.34
    desde
    0.34
    at
    0.31
     أغ
    0.31
    ının
    0.31
    क्लेव
    0.31
    چان
    0.31
    même
    0.31
    Act Density 0.013%

    No Known Activations