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

    Neuronpedia

    INDEX
    Explanations

    you and your capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     superst
    0.34
    㕩
    0.34
    thisTrack
    0.33
     नारेबाजी
    0.33
    roughly
    0.32
    already
    0.32
    뗀
    0.32
    ⇒
    0.32
     webcast
    0.32
     पहली
    0.31
    POSITIVE LOGITS
     AI
    1.09
    AI
    1.08
     Ai
    0.87
    人工智能
    0.86
     chatbot
    0.84
    Ai
    0.83
     bot
    0.82
     GPT
    0.82
     ai
    0.81
    GPT
    0.81
    Act Density 0.151%

    No Known Activations