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

    Neuronpedia

    INDEX
    Explanations

    concepts related to understanding the big picture and holistic viewpoints

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

    big picture and holistic understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xase
    -0.42
     reso
    -0.41
     norman
    -0.40
    eradish
    -0.39
     suff
    -0.39
     merce
    -0.39
     arg
    -0.39
     p
    -0.38
     bede
    -0.38
     tor
    -0.38
    POSITIVE LOGITS
    整體
    0.65
     desmotivaciones
    0.65
     burbujas
    0.64
     Gesamt
    0.61
     pájaro
    0.59
     holistic
    0.58
     keseluruhan
    0.57
     Ganzen
    0.57
     totalidad
    0.56
     integridad
    0.56
    Act Density 0.135%

    No Known Activations