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

    Neuronpedia

    INDEX
    Explanations

    objective

    np_max-act · gemini-2.0-flash

    This neuron detects the phrasing introducing a study’s aim (e.g. “Our objective was to …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (Utils
    -0.07
     Fallout
    -0.07
    럼
    -0.06
     analiz
    -0.06
    Products
    -0.06
    (Canvas
    -0.06
    =form
    -0.06
     Adidas
    -0.06
    (ele
    -0.06
    YD
    -0.06
    POSITIVE LOGITS
     했
    0.07
    εκ
    0.07
    uib
    0.06
    uem
    0.06
    오는
    0.06
    todos
    0.06
    walking
    0.06
    측
    0.06
    �
    0.06
    NewLabel
    0.06
    Act Density 0.010%

    No Known Activations