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

    Neuronpedia

    INDEX
    Explanations

    time durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.33
    </h2>
    0.33
    </h3>
    0.32
    یت
    0.31
    azione
    0.30
    uição
    0.30
    би
    0.30
    ām
    0.29
    </strong>
    0.29
    ión
    0.29
    POSITIVE LOGITS
     years
    0.35
    ر
    0.31
    ת
    0.31
    ,
    0.31
     decades
    0.30
    ্ল
    0.29
    ্ম
    0.29
    т
    0.29
     Years
    0.28
     interne
    0.28
    Act Density 0.270%

    No Known Activations