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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries, particularly those seeking explanations or answers

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

    Quoted questions with follow-up text

    np_acts-logits-general · gemini-2.0-flash

    questions followed by answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.81
     Trotzdem
    -0.81
     entanto
    -0.73
    Поэтому
    -0.69
    لكن
    -0.69
     Dennoch
    -0.68
     therefore
    -0.68
     but
    -0.68
     uintptr
    -0.66
     zudem
    -0.66
    POSITIVE LOGITS
    Depends
    1.03
     Depends
    1.00
    Probably
    0.99
     Probably
    0.93
     depends
    0.92
    Pues
    0.90
    很简单
    0.89
    Basically
    0.88
     basically
    0.87
    うーん
    0.86
    Act Density 0.256%

    No Known Activations