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

    Neuronpedia

    INDEX
    Explanations

    citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ائب
    0.47
    सेवा
    0.47
    㕮
    0.46
     घेत
    0.45
    噘
    0.43
    脌
    0.43
     ⏮
    0.43
    荠
    0.43
    🕘
    0.41
    偪
    0.41
    POSITIVE LOGITS
    {
    0.55
    PhysRev
    0.51
    cite
    0.51
    doi
    0.47
     doi
    0.45
     {
    0.45
    Wu
    0.44
    [\
    0.43
     papers
    0.43
    wang
    0.43
    Act Density 0.001%

    No Known Activations