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

    Neuronpedia

    INDEX
    Explanations

    references to ownership and possessive language

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

    Possessive pronouns and related nouns

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⁡
    -0.49
    例の
    -0.47
    fige
    -0.47
    Persist
    -0.47
     campana
    -0.47
    =".
    -0.46
     localizar
    -0.44
    ardı
    -0.44
     ilg
    -0.44
    каз
    -0.44
    POSITIVE LOGITS
    tvguidetime
    0.65
    存于互联网档案馆
    0.64
    providedIn
    0.63
    ſelf
    0.63
    GHIJKLM
    0.61
     photolibrary
    0.60
     senses
    0.60
     iconTwitter
    0.60
    Witam
    0.59
     relationships
    0.59
    Act Density 0.227%

    No Known Activations