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

    Neuronpedia

    INDEX
    Explanations

    code related to the implementation and functionality of plugins, particularly in gaming contexts.

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

    linking actions or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вами
    0.24
     Dacă
    0.23
     आणि
    0.23
     Якщо
    0.22
     şeyi
    0.22
     già
    0.21
     inalámb
    0.21
     如果
    0.21
     نہیں۔
    0.21
     saben
    0.21
    POSITIVE LOGITS
     provide
    0.37
     provides
    0.32
     facilitate
    0.29
    provide
    0.28
     encourage
    0.26
     promote
    0.26
     encourages
    0.26
    ov
    0.26
     have
    0.25
    provides
    0.25
    Act Density 0.713%

    No Known Activations