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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the words "this" and "that."

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

    demonstratives or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.65
     Мексичка
    -0.54
     مشين
    -0.53
     onData
    -0.53
    enderror
    -0.52
    ագրություններ
    -0.52
    ]=>
    -0.50
     noDo
    -0.50
    utel
    -0.49
    Чыгана
    -0.48
    POSITIVE LOGITS
     at
    0.43
     Ganze
    0.42
     in
    0.40
     with
    0.40
     from
    0.39
     during
    0.39
     within
    0.37
     Gegenteil
    0.37
     systematically
    0.37
     nahilalakip
    0.37
    Act Density 0.047%

    No Known Activations