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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "center" and its variations in different contexts

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

    center of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pato
    -0.48
    IOException
    -0.47
    unlikely
    -0.47
     Scottish
    -0.47
    royd
    -0.46
     Dawkins
    -0.45
    isPlaying
    -0.45
     Liam
    -0.44
    Scottish
    -0.43
     gdyby
    -0.43
    POSITIVE LOGITS
     Center
    1.30
    Center
    1.23
     center
    1.16
    center
    1.15
     CENTER
    1.10
     Centre
    1.08
    Centre
    1.01
    CENTER
    1.00
     Centers
    1.00
     centers
    0.97
    Act Density 0.012%

    No Known Activations