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

    Neuronpedia

    INDEX
    Explanations

    Code, data, names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :✨
    -0.75
    Datuak
    -0.71
    IFICATE
    -0.66
    seamnă
    -0.64
     DEPOSITORY
    -0.59
    RenderAtEndOf
    -0.58
     picioare
    -0.57
     виправивши
    -0.57
    Portale
    -0.56
    IMENTAL
    -0.56
    POSITIVE LOGITS
    THE
    0.73
    IT
    0.62
     THE
    0.60
    WHO
    0.59
    HOW
    0.59
    WHY
    0.56
     HOW
    0.56
    AN
    0.55
    CAN
    0.55
    ↵
    0.54
    Act Density 0.003%

    No Known Activations