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

    Neuronpedia

    INDEX
    Explanations

    technical terms and references related to programming, data handling, and computer systems

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

    Non-English words

    np_acts-logits-general · gemini-2.0-flash

    plural nouns and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     herself
    -1.28
     ellas
    -1.13
     she
    -1.13
    脚注の使い方
    -1.04
     która
    -1.03
    herself
    -1.02
     shes
    -1.01
     celles
    -1.00
     éstas
    -0.96
    Elles
    -0.96
    POSITIVE LOGITS
     quelli
    0.65
     eux
    0.54
     it
    0.53
     its
    0.52
    its
    0.51
     którzy
    0.51
     kurie
    0.50
     koji
    0.49
     који
    0.48
     חיצוניים
    0.48
    Act Density 0.028%

    No Known Activations