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

    Neuronpedia

    INDEX
    Explanations

    complex issues/concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istical
    -0.07
     польз
    -0.07
     payroll
    -0.07
    |$
    -0.06
     clothing
    -0.06
    ательно
    -0.06
    ника
    -0.06
     sticker
    -0.06
    ниця
    -0.06
    toy
    -0.06
    POSITIVE LOGITS
     nfs
    0.07
    .getActive
    0.06
     herd
    0.06
    Ｄ
    0.06
     fot
    0.06
     신입
    0.06
    >';↵
    0.06
    [char
    0.06
     MÜ
    0.06
     @"";↵
    0.06
    Act Density 0.087%

    No Known Activations