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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence and significance of entities or actions in a context

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

    pronoun followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.36
    jango
    -0.34
    ={<
    -0.31
    TypedDataSet
    -0.31
    gdx
    -0.31
     bộ
    -0.31
     ſmall
    -0.31
    addContainerGap
    -0.30
     sério
    -0.30
     relâche
    -0.29
    POSITIVE LOGITS
     مشين
    0.58
     ujednoznacz
    0.57
     виправивши
    0.51
    تقاوى
    0.50
     <>",
    0.50
    Referanser
    0.49
     Infórmanos
    0.48
     salarios
    0.47
    matchCondition
    0.47
    bürgermeister
    0.47
    Act Density 0.460%

    No Known Activations