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

    Neuronpedia

    INDEX
    Explanations

    AI assistants and chatbots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    谤
    0.42
    謗
    0.40
    രള
    0.40
     konnten
    0.40
     fundamentales
    0.39
     pious
    0.38
    頚
    0.38
    났
    0.38
     vuttam
    0.38
     शख
    0.37
    POSITIVE LOGITS
     assistant
    0.50
     ChatGPT
    0.50
     Assistant
    0.49
     workspace
    0.49
    ChatGPT
    0.49
    Assistant
    0.47
     Workspace
    0.47
     AI
    0.46
     Assistants
    0.45
    AI
    0.45
    Act Density 0.000%

    No Known Activations