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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating recognition or acknowledgment of entities and contributions

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

    recognize forms of recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cost
    -0.40
    PreferredItem
    -0.40
     Cost
    -0.38
     probado
    -0.37
     امريكا
    -0.37
    Cost
    -0.36
     Output
    -0.34
    cost
    -0.34
    Availability
    -0.34
    enschutzer
    -0.33
    POSITIVE LOGITS
     recognizing
    1.57
     recognition
    1.57
     recognize
    1.54
     recognizes
    1.48
     recognized
    1.47
     RECOGN
    1.45
     Recognize
    1.44
     Recognition
    1.44
    Recognition
    1.40
     recognise
    1.39
    Act Density 0.054%

    No Known Activations