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

    Neuronpedia

    INDEX
    Explanations

    occurrences of Japanese verbs and related adjectives or nouns

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

    生まれになって / 好きでした / 寂しすぎる / 嫌がらせ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.65
     defaultstate
    -0.59
     Paglinawan
    -0.59
    extAlignment
    -0.57
    rungsseite
    -0.57
    :+:
    -0.53
    tanleria
    -0.53
     Signalez
    -0.51
    лтемелер
    -0.50
    httphttps
    -0.49
    POSITIVE LOGITS
    게
    0.43
     दर्ज
    0.43
     Agent
    0.42
    sched
    0.42
     Sick
    0.41
    guous
    0.41
    ͜
    0.41
    AccessFile
    0.40
     Lemma
    0.40
    पित
    0.40
    Act Density 0.016%

    No Known Activations