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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or positive emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressing gladness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rüyada
    -0.46
     Seorang
    -0.34
     يتيمه
    -0.34
    grà
    -0.34
    rittura
    -0.32
     vainqueur
    -0.32
    rinha
    -0.31
    WriteAttribute
    -0.31
    RTLD
    -0.30
    kháu
    -0.30
    POSITIVE LOGITS
    __(/*!
    0.55
    GIVEREF
    0.54
     Vikipedi
    0.54
    ftagPool
    0.54
    SpringBootTest
    0.54
    ſelben
    0.51
     متعلقه
    0.50
     سكانية
    0.50
     SqlParameter
    0.48
     EventArgs
    0.47
    Act Density 0.023%

    No Known Activations