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

    Neuronpedia

    INDEX
    Explanations

    neural networks and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EQUAL
    -0.06
    (options
    -0.06
    does
    -0.06
     boosted
    -0.06
    .bad
    -0.06
     lethal
    -0.06
    후
    -0.06
    damage
    -0.06
    224
    -0.06
    sword
    -0.05
    POSITIVE LOGITS
    [,]
    0.07
    marginLeft
    0.07
    .addMouseListener
    0.07
    .relative
    0.07
    ‌رس
    0.06
     выпол
    0.06
    .index
    0.06
    .hasMore
    0.06
    CursorPosition
    0.06
     dilig
    0.06
    Act Density 0.231%

    No Known Activations