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

    Neuronpedia

    INDEX
    Explanations

    Store

    np_max-act · gemini-2.0-flash

    The neuron activates on references to picking or grabbing images from the “gallery” (e.g. Gallery, grabImageFromGallery, ACTION_PICK from MediaStore).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pixels
    -0.07
    ected
    -0.07
    wolf
    -0.07
    oused
    -0.07
     cable
    -0.07
     moving
    -0.06
     Bout
    -0.06
     буду
    -0.06
     고
    -0.06
    esp
    -0.06
    POSITIVE LOGITS
    jandro
    0.06
    unuz
    0.06
    fov
    0.06
    _INFINITY
    0.06
     announcing
    0.06
     composed
    0.06
    SEQU
    0.06
     env
    0.06
     subclass
    0.06
    oldown
    0.06
    Act Density 0.005%

    No Known Activations