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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals and places

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

    Names (often followed by a comma)

    np_acts-logits-general · gemini-2.0-flash

    names like hank name hank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.51
    Склад
    -0.42
     &___
    -0.41
     للمعارف
    -0.40
    béco
    -0.37
    ruptedException
    -0.36
    GrantedAuthority
    -0.35
     precision
    -0.35
     ins
    -0.34
    BagConstraints
    -0.34
    POSITIVE LOGITS
    Dave
    0.53
     Partai
    0.50
     wikipagina
    0.50
    Vidite
    0.49
    liferay
    0.48
     déput
    0.48
     Dave
    0.47
    parsedMessage
    0.46
    */
    0.46
    knapp
    0.46
    Act Density 0.414%

    No Known Activations