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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts and operations

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

    mathematical power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CDCl
    -0.42
     Meksi
    -0.41
     Worker
    -0.41
     pantai
    -0.40
     recic
    -0.40
     Zusammen
    -0.39
     IBOutlet
    -0.39
     rechazar
    -0.39
     muerta
    -0.39
     yeşil
    -0.38
    POSITIVE LOGITS
     power
    0.82
     pow
    0.72
    pow
    0.70
    power
    0.68
    Pow
    0.65
    Power
    0.65
     Power
    0.64
     POWER
    0.61
     Pow
    0.61
    POWER
    0.60
    Act Density 0.154%

    No Known Activations