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

    Neuronpedia

    INDEX
    Explanations

    AI models

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     модель
    0.65
     model
    0.59
    Model
    0.55
     institute
    0.55
     মডেল
    0.55
     nk
    0.55
     RESERVE
    0.54
    model
    0.52
     моде
    0.51
     Model
    0.51
    POSITIVE LOGITS
     ChatGPT
    1.12
     Bard
    1.11
     GPT
    1.06
    ChatGPT
    1.03
    Bard
    0.99
     Claude
    0.98
    GPT
    0.97
    Claude
    0.96
    bard
    0.91
     bard
    0.89
    Act Density 0.417%

    No Known Activations