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

    Neuronpedia

    INDEX
    Explanations

    print commands

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сын
    -0.07
    MemoryWarning
    -0.07
    deny
    -0.07
    cesso
    -0.07
    idine
    -0.07
    Pedido
    -0.07
    FPS
    -0.07
    .freeze
    -0.07
    aec
    -0.07
    .gwt
    -0.07
    POSITIVE LOGITS
    看出
    0.08
    一线
    0.08
    -document
    0.08
     AN
    0.07
     updater
    0.07
    UT
    0.07
    ঙ
    0.07
     Predator
    0.07
     AR
    0.07
    做了
    0.07
    Act Density 0.025%

    No Known Activations