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

    Neuronpedia

    INDEX
    Explanations

    references to legal agreements or contracts

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

    Follows "end" or "Com"

    np_acts-logits-general · gemini-2.0-flash

    have been, gave birth, operating under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OrFail
    -0.59
    InstanceState
    -0.55
     ModelExpression
    -0.55
    siao
    -0.53
     
    -0.53
    LikeLiked
    -0.53
    AndEndTag
    -0.51
    AutoresizingMask
    -0.51
    ustimmung
    -0.50
    وردار
    -0.49
    POSITIVE LOGITS
      
    1.27
    saraba
    0.63
     Extragalactic
    0.56
     kasarigan
    0.56
    تقاوى
    0.55
     distanciation
    0.55
    Upgrade
    0.53
     HasFactory
    0.49
       
    0.49
     мәкал
    0.45
    Act Density 0.249%

    No Known Activations