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

    Neuronpedia

    INDEX
    Explanations

    references and metadata in the text

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

    annotated references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.58
     ayudará
    -0.51
     negociaciones
    -0.49
     banget
    -0.48
    volles
    -0.47
     pemikiran
    -0.47
     pikiran
    -0.47
     bankası
    -0.46
     ibunya
    -0.46
    BorderFactory
    -0.46
    POSITIVE LOGITS
    @{
    0.60
     @{
    0.59
    Население
    0.55
     *@
    0.54
    ])]
    0.54
    @[
    0.54
     @}
    0.50
    ">@
    0.50
     @
    0.49
     @[
    0.46
    Act Density 0.388%

    No Known Activations