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

    Neuronpedia

    INDEX
    Explanations

    code fragments

    np_max-act · gemini-2.0-flash

    The neuron detects the assistant’s refusal or apology statements when declining inappropriate or disallowed requests.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unresolved
    -0.07
    服务器
    -0.06
    оряд
    -0.06
    一度
    -0.06
    _LCD
    -0.06
     effortlessly
    -0.06
     stripes
    -0.06
     xung
    -0.06
    (src
    -0.06
    ublik
    -0.06
    POSITIVE LOGITS
    cantidad
    0.07
    .Floor
    0.07
     getP
    0.06
     Crush
    0.06
    ').'</
    0.06
    ルの
    0.06
    еления
    0.06
    .Override
    0.06
    alse
    0.06
     heal
    0.06
    Act Density 0.027%

    No Known Activations