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

    Neuronpedia

    INDEX
    Explanations

    integrals and antiderivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     n
    0.61
    Screen
    0.57
    ]
    0.57
     {
    0.56
    {
    0.56
    ionar
    0.55
    bangan
    0.53
    octrl
    0.52
    🌋
    0.52
    に向け
    0.51
    POSITIVE LOGITS
     Bantu
    0.53
    vid
    0.50
     integrals
    0.50
     Pendant
    0.49
     )।
    0.49
     。,
    0.48
    ধর্ম
    0.48
     Шта
    0.48
    다
    0.48
    彪
    0.47
    Act Density 0.019%

    No Known Activations