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

    Neuronpedia

    INDEX
    Explanations

    react component functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.68
     niedrig
    0.59
    </h3>
    0.59
    șit
    0.58
    și
    0.54
     जब
    0.53
     jati
    0.53
    vič
    0.53
     copii
    0.53
    ='.
    0.52
    POSITIVE LOGITS
    n
    0.65
    结构的
    0.58
    ╁
    0.55
    to
    0.52
    ческой
    0.52
    {
    0.50
     działal
    0.49
    l
    0.48
    <0x98>
    0.47
    (
    0.47
    Act Density 0.001%

    No Known Activations