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

    Neuronpedia

    INDEX
    Explanations

    references to specific names and titles

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

    tables or figures within text

    np_acts-logits-general · gemini-2.0-flash

    tables and figures references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.58
    MLLoader
    -0.51
    Tagged
    -0.51
    ListModule
    -0.49
    zeß
    -0.48
     ++)
    -0.47
     متعلقه
    -0.45
    Kanpo
    -0.43
     التجار
    -0.42
    differential
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    0.74
    saraba
    0.72
     itſelf
    0.69
    UnknownFieldSet
    0.67
    RectangleBorder
    0.61
     ffilmiau
    0.60
    KURZBESCHREIBUNG
    0.59
     ſeveral
    0.59
    RenderAtEndOf
    0.59
    loroethene
    0.59
    Act Density 0.068%

    No Known Activations