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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash

    The neuron detects the standard real-estate listing disclaimer and attribution text (e.g., IDX/Data Exchange “information is provided…non-commercial use” boilerplate).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     그림
    -0.07
     leader
    -0.07
     shot
    -0.07
     Speaking
    -0.07
    -flow
    -0.06
    وس
    -0.06
     voxel
    -0.06
    сен
    -0.06
     BL
    -0.06
    perc
    -0.06
    POSITIVE LOGITS
    =forms
    0.07
    maxcdn
    0.07
    FetchRequest
    0.07
    (blank
    0.06
    =size
    0.06
     entityManager
    0.06
    웃
    0.06
    การใช
    0.06
     giz
    0.06
     آزمون
    0.06
    Act Density 0.008%

    No Known Activations