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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire and personal opinions

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

    that's why that can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.65
     незавершена
    -0.65
    хьтан
    -0.57
     Chwiliwch
    -0.53
     חיצוניים
    -0.53
    MessageTagHelper
    -0.52
    ValueStyle
    -0.50
    ffilm
    -0.48
    httphttps
    -0.48
    ‌پدی
    -0.47
    POSITIVE LOGITS
    latego
    0.51
     Deshalb
    0.46
     مشين
    0.45
     deshalb
    0.43
     deswegen
    0.43
     setInterval
    0.41
    SBATCH
    0.39
    MathML
    0.38
     Daarom
    0.37
    OrNil
    0.35
    Act Density 0.025%

    No Known Activations