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

    Neuronpedia

    INDEX
    Explanations

    affirmative expressions of agreement or acknowledgment

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

    I have seen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    devamını
    -0.75
    writeFieldEnd
    -0.67
    Tembelea
    -0.66
     defaultstate
    -0.65
     betweenstory
    -0.65
    fromnode
    -0.65
     Мексичка
    -0.62
     otomatig
    -0.61
     OFDb
    -0.61
     Wikimedijinoj
    -0.59
    POSITIVE LOGITS
     
    0.36
      
    0.35
    目
    0.35
     sk
    0.34
     off
    0.33
    SharedCtor
    0.33
    取
    0.32
     vis
    0.30
    DisplayMode
    0.30
    Exact
    0.30
    Act Density 0.020%

    No Known Activations