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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iled
    -0.07
    learn
    -0.07
    ρ
    -0.07
     là
    -0.07
    _cross
    -0.07
    Learn
    -0.06
     انت
    -0.06
     çalışan
    -0.06
    _i
    -0.06
    =t
    -0.06
    POSITIVE LOGITS
    save
    0.09
    形式
    0.06
    」と
    0.06
    .mkdirs
    0.06
    Davis
    0.06
     indictment
    0.06
    robot
    0.06
     "|"
    0.06
    ucker
    0.06
     Пет
    0.06
    Act Density 0.011%

    No Known Activations