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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions indicating relationships and emotional connections

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

    Japanese question and uncertainty endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aholisi
    -0.68
    httphttps
    -0.64
    はじめに
    -0.59
     незавершена
    -0.58
    しますが
    -0.57
    ましたが
    -0.56
    いましたが
    -0.56
    りますが
    -0.53
     kaarangay
    -0.52
    りましたが
    -0.52
    POSITIVE LOGITS
    RenderAtEndOf
    0.45
     način
    0.38
     pertenece
    0.37
     literaria
    0.37
     Bidang
    0.34
    ąz
    0.34
     knji
    0.34
     sobra
    0.34
     cardíaca
    0.34
     chevaux
    0.33
    Act Density 0.071%

    No Known Activations