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

    Neuronpedia

    INDEX
    Explanations

    specific references to health-related projects and methodologies

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

    after certain capitalized tokens

    np_acts-logits-general · gemini-2.0-flash

    foreign language terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ,
    -0.55
    <bos>
    -0.53
    .
    -0.53
    ↵↵
    -0.53
     "
    -0.52
     :
    -0.51
    ↵
    -0.50
     -
    -0.50
     
    -0.49
     ...
    -0.49
    POSITIVE LOGITS
     kysy
    0.35
     šķ
    0.30
     femininas
    0.30
     aikaa
    0.29
     bēr
    0.28
     vandens
    0.28
     jäsen
    0.27
     vastaan
    0.26
     näky
    0.26
     päivä
    0.26
    Act Density 24.943%

    No Known Activations