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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms and conditions

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

    Following pronouns, conjunctions, or sentence fragments

    np_acts-logits-general · gemini-2.0-flash

    first person pronouns / technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.78
     appunto
    -0.77
    wnież
    -0.73
    ."""
    -0.71
    存于互联网档案馆
    -0.70
    URLException
    -0.70
     ujednoznacz
    -0.69
    .*/
    -0.66
    parsedMessage
    -0.66
     également
    -0.65
    POSITIVE LOGITS
     absolutely
    0.58
    </b>
    0.56
    [/
    0.55
    ñora
    0.53
     we
    0.52
    We
    0.51
     
    0.51
     [
    0.49
     never
    0.48
     my
    0.48
    Act Density 0.275%

    No Known Activations