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

    Neuronpedia

    INDEX
    Explanations

    references to lists or collections of items in various contexts

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

    adding to lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     termica
    -0.38
     aliento
    -0.36
     térmico
    -0.36
    Inferno
    -0.35
    Wymiary
    -0.34
    請繼續往下閱讀
    -0.33
     Manch
    -0.33
    éget
    -0.33
     recuer
    -0.33
     fully
    -0.33
    POSITIVE LOGITS
     adding
    0.67
    adding
    0.65
     menambahkan
    0.64
     Adding
    0.63
     added
    0.62
    IsMutable
    0.60
     aggiungere
    0.60
    addition
    0.60
     thêm
    0.59
    added
    0.58
    Act Density 0.054%

    No Known Activations