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

    Neuronpedia

    INDEX
    Explanations

    the copula or forms of the verb "to be" in Japanese

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

    japanese copula です

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chofe
    -0.57
    textTheme
    -0.53
    //
    -0.51
     toller
    -0.47
    PMailer
    -0.46
     дописавши
    -0.46
    WriteAttribute
    -0.45
    phage
    -0.45
     rime
    -0.45
    ScopeManager
    -0.45
    POSITIVE LOGITS
    です
    1.30
    だ
    0.82
    입니다
    0.76
    이다
    0.71
     です
    0.62
    さんです
    0.60
    品です
    0.59
    ところです
    0.55
    いです
    0.55
     입니다
    0.54
    Act Density 0.005%

    No Known Activations