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

    Neuronpedia

    INDEX
    Explanations

    the word "one" in various contexts

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

    one of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beleid
    -0.34
    ChromeDriver
    -0.33
     uș
    -0.31
     Mat
    -0.31
     direto
    -0.31
    Související
    -0.29
    욱
    -0.28
     donné
    -0.28
    tr
    -0.28
     wezen
    -0.28
    POSITIVE LOGITS
     betweenstory
    0.91
     témoig
    0.64
    MemoryWarning
    0.62
    <unused51>
    0.62
    <unused79>
    0.61
    <unused41>
    0.61
    <unused43>
    0.61
    <unused23>
    0.61
    <unused3>
    0.61
    <unused14>
    0.61
    Act Density 0.052%

    No Known Activations