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

    Neuronpedia

    INDEX
    Explanations

    cameras and filming

    np_max-act · gemini-2.0-flash

    The neuron activates on words and word pieces that refer to recording or filming—e.g. camera, record/recording, footage, filmed, documenting, GoPro.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    调整
    -0.07
    역시
    -0.07
    -major
    -0.07
    集团
    -0.06
     leap
    -0.06
     객체
    -0.06
    anax
    -0.06
    ת
    -0.06
    ’an
    -0.06
    、や
    -0.06
    POSITIVE LOGITS
    .(
    0.06
    toHave
    0.06
     libido
    0.06
     WB
    0.06
    Slim
    0.06
     cara
    0.06
     slik
    0.06
    ハイ
    0.06
    GridView
    0.06
     Rect
    0.06
    Act Density 0.037%

    No Known Activations