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

    Neuronpedia

    INDEX
    Explanations

    a large language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rows
    0.44
    $(
    0.37
     tweaks
    0.37
     widget
    0.37
     $(
    0.36
     row
    0.36
    bottom
    0.36
     scheint
    0.36
     racking
    0.36
    back
    0.36
    POSITIVE LOGITS
     OpenAI
    0.53
    善良
    0.48
    ปลอดภัย
    0.48
     chatbot
    0.48
     נישט
    0.46
     niemals
    0.46
     deont
    0.46
     abhor
    0.45
     نمی
    0.45
    できません
    0.45
    Act Density 2.107%

    No Known Activations