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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or reactions

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

    followed by names or titles

    np_acts-logits-general · gemini-2.0-flash

    titles and professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     umane
    -0.39
     ludzi
    -0.39
     Iggy
    -0.36
    ształ
    -0.36
    vov
    -0.35
    illerato
    -0.35
    pep
    -0.35
     locos
    -0.35
     Çok
    -0.34
    こういう
    -0.34
    POSITIVE LOGITS
     former
    1.45
    former
    1.28
     fellow
    1.25
     Former
    1.22
     longtime
    1.21
     actress
    1.20
     actor
    1.20
    Former
    1.18
     veteran
    1.17
     guitarist
    1.14
    Act Density 0.456%

    No Known Activations