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

    Neuronpedia

    INDEX
    Explanations

    robustness

    np_max-act · gemini-2.0-flash

    technical terms and concepts related to machine learning algorithms.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Lord
    -0.07
    呼
    -0.07
    Alarm
    -0.07
    _Delay
    -0.06
     Pedido
    -0.06
    單
    -0.06
    INGLE
    -0.06
     hlad
    -0.06
     daylight
    -0.06
     breathe
    -0.06
    POSITIVE LOGITS
     ActionTypes
    0.07
     <!--[
    0.07
    .Func
    0.06
    .getElement
    0.06
    ARDS
    0.06
    шем
    0.06
     TAB
    0.06
     тоб
    0.06
     objc
    0.06
     drugs
    0.06
    Act Density 0.006%

    No Known Activations