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

    Neuronpedia

    INDEX
    Explanations

    tools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    YT
    -0.07
    Tp
    -0.07
    finally
    -0.07
     trav
    -0.06
    /detail
    -0.06
    เฉพาะ
    -0.06
    생님
    -0.06
    <usize
    -0.06
    िच
    -0.06
    okane
    -0.06
    POSITIVE LOGITS
     Європ
    0.07
     resilient
    0.06
    Margin
    0.06
     Library
    0.06
    .Program
    0.06
     requiring
    0.06
     Clients
    0.06
    (Board
    0.06
     Drill
    0.06
     groundbreaking
    0.06
    Act Density 0.016%

    No Known Activations