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

    Neuronpedia

    INDEX
    Explanations

    chat and chatbots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ovsky
    0.40
    ChatMessage
    0.40
     Mussolini
    0.40
     reservoir
    0.39
     layi
    0.39
    mui
    0.39
     huk
    0.38
     efektif
    0.38
    聊
    0.38
     nostrils
    0.38
    POSITIVE LOGITS
    تس
    0.46
    たま
    0.45
    봐
    0.44
     PHONE
    0.43
    tut
    0.41
    Tut
    0.40
     Phone
    0.40
    討論
    0.38
    と呼ばれる
    0.38
    तुम
    0.38
    Act Density 0.000%

    No Known Activations