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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staffer
    -0.07
     noted
    -0.07
     TIMESTAMP
    -0.07
    signin
    -0.06
    main
    -0.06
     undermines
    -0.06
    ulings
    -0.06
    <ID
    -0.06
    osloven
    -0.06
     planners
    -0.06
    POSITIVE LOGITS
    GO
    0.07
     málo
    0.07
    ỗng
    0.07
     Except
    0.06
     Jakarta
    0.06
    Correo
    0.06
     สร
    0.06
    %.↵↵
    0.06
    terdam
    0.06
     değildir
    0.06
    Act Density 0.006%

    No Known Activations