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

    Neuronpedia

    INDEX
    Explanations

    references to time-related events and measurements

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

    after common prepositions

    np_acts-logits-general · gemini-2.0-flash

    specific context, foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sstream
    -0.40
    ++++++++++++++++
    -0.34
    saraba
    -0.31
     års
    -0.31
     térmico
    -0.31
     oublié
    -0.30
    cupa
    -0.30
    ourites
    -0.30
     aérea
    -0.30
    defs
    -0.30
    POSITIVE LOGITS
    rungsseite
    0.68
    AnimationsModule
    0.55
     arşivlendi
    0.54
    Спасылкі
    0.53
     canlynol
    0.52
     referenties
    0.52
    WithMany
    0.52
    Portály
    0.51
     оригіналу
    0.51
     desmotivaciones
    0.51
    Act Density 1.664%

    No Known Activations