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

    Neuronpedia

    INDEX
    Explanations

    domain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sailors
    -0.07
    022
    -0.07
     zurück
    -0.07
    className
    -0.06
    sym
    -0.06
    691
    -0.06
    腕
    -0.06
    rebbe
    -0.06
    .person
    -0.06
    Employees
    -0.06
    POSITIVE LOGITS
     лечение
    0.07
     Sampling
    0.07
    .requestFocus
    0.07
    ע
    0.07
    jest
    0.07
    CLUD
    0.07
    .addMouseListener
    0.06
    ρη
    0.06
    лятор
    0.06
    .DAL
    0.06
    Act Density 0.005%

    No Known Activations