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

    Neuronpedia

    INDEX
    Explanations

    comparisons and distinctions between similar concepts or items

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

    different vs same

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     healthier
    -0.56
     Stronger
    -0.56
     quicker
    -0.54
     stronger
    -0.54
     sharper
    -0.53
    devamını
    -0.53
     brighter
    -0.52
     bättre
    -0.52
     happier
    -0.52
     funnier
    -0.52
    POSITIVE LOGITS
    AndEndTag
    0.45
    Panamoan
    0.39
    /**
    0.37
     Pandey
    0.37
     сом
    0.36
     lunches
    0.36
     <>",
    0.36
    长的
    0.35
     Италијани
    0.35
     وتسجيلات
    0.35
    Act Density 0.447%

    No Known Activations