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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or paragraphs in the text

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

    bench, cortex, intelligent, purchase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apimachinery
    -0.81
     kiin
    -0.64
     mérit
    -0.63
    tvguidetime
    -0.63
    скажите
    -0.59
     refusé
    -0.59
     partagé
    -0.58
    StoryboardSegue
    -0.58
    webElementXpaths
    -0.58
    mybatisplus
    -0.58
    POSITIVE LOGITS
     training
    0.55
     study
    0.53
    keras
    0.52
     run
    0.48
     marathon
    0.48
     tensorflow
    0.48
     results
    0.47
    研究院
    0.46
     studies
    0.46
     learning
    0.45
    Act Density 0.062%

    No Known Activations